Multi-Class Deep Learning Model for Sign Language MNIST Using TensorFlow Take 1

David Lowe

November 19, 2020

Template Credit: Adapted from a template made available by Dr. Jason Brownlee of Machine Learning Mastery. [https://machinelearningmastery.com/]

SUMMARY: The project aims to construct a predictive model using various machine learning algorithms and document the end-to-end steps using a template. The Sign Language MNIST dataset is a multi-class classification situation where we attempt to predict one of several (more than two) possible outcomes.

INTRODUCTION: The original MNIST image dataset of handwritten digits is a popular benchmark for image-based machine learning methods. The Sign Language MNIST is presented here and follows the same CSV format with labels and pixel values in single rows to stimulate the community to develop more drop-in replacements. The American Sign Language letter database of hand gestures represent a multi-class problem with 24 classes of letters (excluding J and Z, which require motion).

The dataset format is patterned to match closely with the classic MNIST. Each training and test case represents a label (0-25) as a one-to-one map for each alphabetic letter A-Z (and no cases for 9=J or 25=Z because of gesture motions). The training data (27,455 cases) and test data (7172 instances) are approximately half the size of the standard MNIST but otherwise similar with a header row of the labels, pixel1,pixel2….pixel784 which represent a single 28x28 pixel image with grayscale values between 0-255. The original hand gesture image data represented multiple users repeating the gesture against different backgrounds.

In this Take1 iteration, we will construct a Multilayer Perceptron (MLP) model with five hidden layers to model this dataset.

ANALYSIS: In this Take1 iteration, the MLP model's performance achieved an accuracy score of 94.93% after 50 epochs using the training dataset. The same model processed the test dataset with an accuracy score of 77.93%, which pointed to a high variance error.

CONCLUSION: In this iteration, the TensorFlow MLP model did not appear to be suitable for modeling this dataset. We should consider experimenting another algorithm with this dataset.

Dataset Used: Sign Language MNIST Dataset

Dataset ML Model: Multi-class classification with numerical attributes

Dataset Reference: https://www.kaggle.com/datamunge/sign-language-mnist

One source of potential performance benchmarks: https://www.kaggle.com/datamunge/sign-language-mnist

A deep-learning modeling project generally can be broken down into five major tasks:

1. Prepare Environment
2. Summarize and Visualize Data
3. Pre-process Data
4. Train and Evaluate Models
5. Finalize Model and Present Analysis

Task 1 - Prepare Environment

# Install the packages to support accessing environment variable and SQL databases
!pip install python-dotenv PyMySQL boto3

Collecting python-dotenv
  Downloading https://files.pythonhosted.org/packages/32/2e/e4585559237787966aad0f8fd0fc31df1c4c9eb0e62de458c5b6cde954eb/python_dotenv-0.15.0-py2.py3-none-any.whl
Collecting PyMySQL
  Downloading https://files.pythonhosted.org/packages/1a/ea/dd9c81e2d85efd03cfbf808736dd055bd9ea1a78aea9968888b1055c3263/PyMySQL-0.10.1-py2.py3-none-any.whl (47kB)
     |████████████████████████████████| 51kB 5.5MB/s 
Collecting boto3
  Downloading https://files.pythonhosted.org/packages/b2/f7/a0f1e13222e10d426afbc50fc7de3c65acafa6ff4cc790e71e649d4cd9ad/boto3-1.16.15-py2.py3-none-any.whl (129kB)
     |████████████████████████████████| 133kB 14.3MB/s 
Collecting botocore<1.20.0,>=1.19.15
  Downloading https://files.pythonhosted.org/packages/f4/1d/bed1bb297abadc387d8328d88ac7612daa2d9f716bd83ec096ceb4a9f8bb/botocore-1.19.15-py2.py3-none-any.whl (6.7MB)
     |████████████████████████████████| 6.7MB 14.6MB/s 
Collecting jmespath<1.0.0,>=0.7.1
  Downloading https://files.pythonhosted.org/packages/07/cb/5f001272b6faeb23c1c9e0acc04d48eaaf5c862c17709d20e3469c6e0139/jmespath-0.10.0-py2.py3-none-any.whl
Collecting s3transfer<0.4.0,>=0.3.0
  Downloading https://files.pythonhosted.org/packages/69/79/e6afb3d8b0b4e96cefbdc690f741d7dd24547ff1f94240c997a26fa908d3/s3transfer-0.3.3-py2.py3-none-any.whl (69kB)
     |████████████████████████████████| 71kB 7.3MB/s 
Requirement already satisfied: python-dateutil<3.0.0,>=2.1 in /usr/local/lib/python3.6/dist-packages (from botocore<1.20.0,>=1.19.15->boto3) (2.8.1)
Collecting urllib3<1.26,>=1.25.4; python_version != "3.4"
  Downloading https://files.pythonhosted.org/packages/56/aa/4ef5aa67a9a62505db124a5cb5262332d1d4153462eb8fd89c9fa41e5d92/urllib3-1.25.11-py2.py3-none-any.whl (127kB)
     |████████████████████████████████| 133kB 52.6MB/s 
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.6/dist-packages (from python-dateutil<3.0.0,>=2.1->botocore<1.20.0,>=1.19.15->boto3) (1.15.0)
ERROR: datascience 0.10.6 has requirement folium==0.2.1, but you'll have folium 0.8.3 which is incompatible.
Installing collected packages: python-dotenv, PyMySQL, urllib3, jmespath, botocore, s3transfer, boto3
  Found existing installation: urllib3 1.24.3
    Uninstalling urllib3-1.24.3:
      Successfully uninstalled urllib3-1.24.3
Successfully installed PyMySQL-0.10.1 boto3-1.16.15 botocore-1.19.15 jmespath-0.10.0 python-dotenv-0.15.0 s3transfer-0.3.3 urllib3-1.25.11

# Retrieve GPU configuration information from Colab
gpu_info = !nvidia-smi
gpu_info = '\n'.join(gpu_info)
if gpu_info.find('failed') >= 0:
    print('Select the Runtime → "Change runtime type" menu to enable a GPU accelerator, ')
    print('and then re-execute this cell.')
else:
    print(gpu_info)

Wed Nov 11 01:51:04 2020       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 455.32.00    Driver Version: 418.67       CUDA Version: 10.1     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  Tesla V100-SXM2...  Off  | 00000000:00:04.0 Off |                    0 |
| N/A   37C    P0    23W / 300W |      0MiB / 16130MiB |      0%      Default |
|                               |                      |                 ERR! |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

# Retrieve memory configuration information from Colab
from psutil import virtual_memory
ram_gb = virtual_memory().total / 1e9
print('Your runtime has {:.1f} gigabytes of available RAM\n'.format(ram_gb))

if ram_gb < 20:
    print('To enable a high-RAM runtime, select the Runtime → "Change runtime type"')
    print('menu, and then select High-RAM in the Runtime shape dropdown. Then, ')
    print('re-execute this cell.')
else:
    print('You are using a high-RAM runtime!')

Your runtime has 13.7 gigabytes of available RAM

To enable a high-RAM runtime, select the Runtime → "Change runtime type"
menu, and then select High-RAM in the Runtime shape dropdown. Then, 
re-execute this cell.

# Direct Colab to use TensorFlow v2
# %tensorflow_version 2.x

# Retrieve CPU information from the system
ncpu = !nproc
print("The number of available CPUs is:", ncpu[0])

The number of available CPUs is: 2

1.a) Load libraries and modules

# Set the random seed number for reproducible results
seedNum = 888

# Load libraries and packages
import random
random.seed(seedNum)
import numpy as np
np.random.seed(seedNum)
import pandas as pd
import matplotlib.pyplot as plt
import os
import sys
import boto3
from datetime import datetime
from dotenv import load_dotenv
from sklearn import preprocessing
from sklearn.model_selection import train_test_split
from sklearn.model_selection import RepeatedKFold
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.compose import ColumnTransformer
# from imblearn.pipeline import Pipeline
# from imblearn.over_sampling import SMOTE
# from imblearn.under_sampling import RandomUnderSampler
import tensorflow as tf
tf.random.set_seed(seedNum)
from tensorflow import keras

1.b) Set up the controlling parameters and functions

# Begin the timer for the script processing
startTimeScript = datetime.now()

# Set up the number of CPU cores available for multi-thread processing
n_jobs = 1

# Set up the flag to stop sending progress emails (setting to True will send status emails!)
notifyStatus = False

# Set Pandas options
pd.set_option("display.max_rows", None)
pd.set_option("display.max_columns", None)
pd.set_option("display.width", 140)

# Set the percentage sizes for splitting the dataset
test_set_size = 0.2
val_set_size = 0.25

# Set the number of folds and iterations for cross validation
n_folds = 5
n_iterations = 2

# Set various default modeling parameters
default_loss = 'categorical_crossentropy'
default_metrics = ['accuracy']
default_optimizer = tf.keras.optimizers.Adam(learning_rate=0.0001)
default_kernel_init = tf.keras.initializers.GlorotUniform(seed=seedNum)
default_epoch = 50
default_batch = 32

# Define the labels to use for graphing the data
train_metric = "accuracy"
validation_metric = "val_accuracy"
train_loss = "loss"
validation_loss = "val_loss"

# Check the number of GPUs accessible through TensorFlow
print('Num GPUs Available:', len(tf.config.list_physical_devices('GPU')))

# Print out the TensorFlow version for confirmation
print('TensorFlow version:', tf.__version__)

Num GPUs Available: 1
TensorFlow version: 2.3.0

# Set up the parent directory location for loading the dotenv files
# useColab = False
# if useColab:
#     # Mount Google Drive locally for storing files
#     from google.colab import drive
#     drive.mount('/content/gdrive')
#     gdrivePrefix = '/content/gdrive/My Drive/Colab_Downloads/'
#     env_path = '/content/gdrive/My Drive/Colab Notebooks/'
#     dotenv_path = env_path + "python_script.env"
#     load_dotenv(dotenv_path=dotenv_path)

# Set up the dotenv file for retrieving environment variables
# useLocalPC = False
# if useLocalPC:
#     env_path = "/Users/david/PycharmProjects/"
#     dotenv_path = env_path + "python_script.env"
#     load_dotenv(dotenv_path=dotenv_path)

# Set up the email notification function
def status_notify(msg_text):
    access_key = os.environ.get('SNS_ACCESS_KEY')
    secret_key = os.environ.get('SNS_SECRET_KEY')
    aws_region = os.environ.get('SNS_AWS_REGION')
    topic_arn = os.environ.get('SNS_TOPIC_ARN')
    if (access_key is None) or (secret_key is None) or (aws_region is None):
        sys.exit("Incomplete notification setup info. Script Processing Aborted!!!")
    sns = boto3.client('sns', aws_access_key_id=access_key, aws_secret_access_key=secret_key, region_name=aws_region)
    response = sns.publish(TopicArn=topic_arn, Message=msg_text)
    if response['ResponseMetadata']['HTTPStatusCode'] != 200 :
        print('Status notification not OK with HTTP status code:', response['ResponseMetadata']['HTTPStatusCode'])

# Reset the random number generators
def reset_random(x):
    random.seed(x)
    np.random.seed(x)
    tf.random.set_seed(x)

if notifyStatus: status_notify('(TensorFlow Multi-Class) Task 1 - Prepare Environment has begun on ' + datetime.now().strftime('%A %B %d, %Y %I:%M:%S %p'))

1.c) Load Dataset

dataset_path = 'https://dainesanalytics.com/datasets/kaggle-sign-language-mnist/sign_mnist_train.csv'
Xy_original = pd.read_csv(dataset_path, sep=',')

# Take a peek at the dataframe after import
Xy_original.head()

	label	pixel1	pixel2	pixel3	pixel4	pixel5	pixel6	pixel7	pixel8	pixel9	pixel10	pixel11	pixel12	pixel13	pixel14	pixel15	pixel16	pixel17	pixel18	pixel19	pixel20	pixel21	pixel22	pixel23	pixel24	pixel25	pixel26	pixel27	pixel28	pixel29	pixel30	pixel31	pixel32	pixel33	pixel34	pixel35	pixel36	pixel37	pixel38	pixel39	pixel40	pixel41	pixel42	pixel43	pixel44	pixel45	pixel46	pixel47	pixel48	pixel49	pixel50	pixel51	pixel52	pixel53	pixel54	pixel55	pixel56	pixel57	pixel58	pixel59	pixel60	pixel61	pixel62	pixel63	pixel64	pixel65	pixel66	pixel67	pixel68	pixel69	pixel70	pixel71	pixel72	pixel73	pixel74	pixel75	pixel76	pixel77	pixel78	pixel79	pixel80	pixel81	pixel82	pixel83	pixel84	pixel85	pixel86	pixel87	pixel88	pixel89	pixel90	pixel91	pixel92	pixel93	pixel94	pixel95	pixel96	pixel97	pixel98	pixel99	pixel100	pixel101	pixel102	pixel103	pixel104	pixel105	pixel106	pixel107	pixel108	pixel109	pixel110	pixel111	pixel112	pixel113	pixel114	pixel115	pixel116	pixel117	pixel118	pixel119	pixel120	pixel121	pixel122	pixel123	pixel124	pixel125	pixel126	pixel127	pixel128	pixel129	pixel130	pixel131	pixel132	pixel133	pixel134	pixel135	pixel136	pixel137	pixel138	pixel139	pixel140	pixel141	pixel142	pixel143	pixel144	pixel145	pixel146	pixel147	pixel148	pixel149	pixel150	pixel151	pixel152	pixel153	pixel154	pixel155	pixel156	pixel157	pixel158	pixel159	pixel160	pixel161	pixel162	pixel163	pixel164	pixel165	pixel166	pixel167	pixel168	pixel169	pixel170	pixel171	pixel172	pixel173	pixel174	pixel175	pixel176	pixel177	pixel178	pixel179	pixel180	pixel181	pixel182	pixel183	pixel184	pixel185	pixel186	pixel187	pixel188	pixel189	pixel190	pixel191	pixel192	pixel193	pixel194	pixel195	pixel196	pixel197	pixel198	pixel199	pixel200	pixel201	pixel202	pixel203	pixel204	pixel205	pixel206	pixel207	pixel208	pixel209	pixel210	pixel211	pixel212	pixel213	pixel214	pixel215	pixel216	pixel217	pixel218	pixel219	pixel220	pixel221	pixel222	pixel223	pixel224	pixel225	pixel226	pixel227	pixel228	pixel229	pixel230	pixel231	pixel232	pixel233	pixel234	pixel235	pixel236	pixel237	pixel238	pixel239	pixel240	pixel241	pixel242	pixel243	pixel244	pixel245	pixel246	pixel247	pixel248	pixel249	pixel250	pixel251	pixel252	pixel253	pixel254	pixel255	pixel256	pixel257	pixel258	pixel259	pixel260	pixel261	pixel262	pixel263	pixel264	pixel265	pixel266	pixel267	pixel268	pixel269	pixel270	pixel271	pixel272	pixel273	pixel274	pixel275	pixel276	pixel277	pixel278	pixel279	pixel280	pixel281	pixel282	pixel283	pixel284	pixel285	pixel286	pixel287	pixel288	pixel289	pixel290	pixel291	pixel292	pixel293	pixel294	pixel295	pixel296	pixel297	pixel298	pixel299	pixel300	pixel301	pixel302	pixel303	pixel304	pixel305	pixel306	pixel307	pixel308	pixel309	pixel310	pixel311	pixel312	pixel313	pixel314	pixel315	pixel316	pixel317	pixel318	pixel319	pixel320	pixel321	pixel322	pixel323	pixel324	pixel325	pixel326	pixel327	pixel328	pixel329	pixel330	pixel331	pixel332	pixel333	pixel334	pixel335	pixel336	pixel337	pixel338	pixel339	pixel340	pixel341	pixel342	pixel343	pixel344	pixel345	pixel346	pixel347	pixel348	pixel349	pixel350	pixel351	pixel352	pixel353	pixel354	pixel355	pixel356	pixel357	pixel358	pixel359	pixel360	pixel361	pixel362	pixel363	pixel364	pixel365	pixel366	pixel367	pixel368	pixel369	pixel370	pixel371	pixel372	pixel373	pixel374	pixel375	pixel376	pixel377	pixel378	pixel379	pixel380	pixel381	pixel382	pixel383	pixel384	pixel385	pixel386	pixel387	pixel388	pixel389	pixel390	pixel391	pixel392	pixel393	pixel394	pixel395	pixel396	pixel397	pixel398	pixel399	pixel400	pixel401	pixel402	pixel403	pixel404	pixel405	pixel406	pixel407	pixel408	pixel409	pixel410	pixel411	pixel412	pixel413	pixel414	pixel415	pixel416	pixel417	pixel418	pixel419	pixel420	pixel421	pixel422	pixel423	pixel424	pixel425	pixel426	pixel427	pixel428	pixel429	pixel430	pixel431	pixel432	pixel433	pixel434	pixel435	pixel436	pixel437	pixel438	pixel439	pixel440	pixel441	pixel442	pixel443	pixel444	pixel445	pixel446	pixel447	pixel448	pixel449	pixel450	pixel451	pixel452	pixel453	pixel454	pixel455	pixel456	pixel457	pixel458	pixel459	pixel460	pixel461	pixel462	pixel463	pixel464	pixel465	pixel466	pixel467	pixel468	pixel469	pixel470	pixel471	pixel472	pixel473	pixel474	pixel475	pixel476	pixel477	pixel478	pixel479	pixel480	pixel481	pixel482	pixel483	pixel484	pixel485	pixel486	pixel487	pixel488	pixel489	pixel490	pixel491	pixel492	pixel493	pixel494	pixel495	pixel496	pixel497	pixel498	pixel499	pixel500	pixel501	pixel502	pixel503	pixel504	pixel505	pixel506	pixel507	pixel508	pixel509	pixel510	pixel511	pixel512	pixel513	pixel514	pixel515	pixel516	pixel517	pixel518	pixel519	pixel520	pixel521	pixel522	pixel523	pixel524	pixel525	pixel526	pixel527	pixel528	pixel529	pixel530	pixel531	pixel532	pixel533	pixel534	pixel535	pixel536	pixel537	pixel538	pixel539	pixel540	pixel541	pixel542	pixel543	pixel544	pixel545	pixel546	pixel547	pixel548	pixel549	pixel550	pixel551	pixel552	pixel553	pixel554	pixel555	pixel556	pixel557	pixel558	pixel559	pixel560	pixel561	pixel562	pixel563	pixel564	pixel565	pixel566	pixel567	pixel568	pixel569	pixel570	pixel571	pixel572	pixel573	pixel574	pixel575	pixel576	pixel577	pixel578	pixel579	pixel580	pixel581	pixel582	pixel583	pixel584	pixel585	pixel586	pixel587	pixel588	pixel589	pixel590	pixel591	pixel592	pixel593	pixel594	pixel595	pixel596	pixel597	pixel598	pixel599	pixel600	pixel601	pixel602	pixel603	pixel604	pixel605	pixel606	pixel607	pixel608	pixel609	pixel610	pixel611	pixel612	pixel613	pixel614	pixel615	pixel616	pixel617	pixel618	pixel619	pixel620	pixel621	pixel622	pixel623	pixel624	pixel625	pixel626	pixel627	pixel628	pixel629	pixel630	pixel631	pixel632	pixel633	pixel634	pixel635	pixel636	pixel637	pixel638	pixel639	pixel640	pixel641	pixel642	pixel643	pixel644	pixel645	pixel646	pixel647	pixel648	pixel649	pixel650	pixel651	pixel652	pixel653	pixel654	pixel655	pixel656	pixel657	pixel658	pixel659	pixel660	pixel661	pixel662	pixel663	pixel664	pixel665	pixel666	pixel667	pixel668	pixel669	pixel670	pixel671	pixel672	pixel673	pixel674	pixel675	pixel676	pixel677	pixel678	pixel679	pixel680	pixel681	pixel682	pixel683	pixel684	pixel685	pixel686	pixel687	pixel688	pixel689	pixel690	pixel691	pixel692	pixel693	pixel694	pixel695	pixel696	pixel697	pixel698	pixel699	pixel700	pixel701	pixel702	pixel703	pixel704	pixel705	pixel706	pixel707	pixel708	pixel709	pixel710	pixel711	pixel712	pixel713	pixel714	pixel715	pixel716	pixel717	pixel718	pixel719	pixel720	pixel721	pixel722	pixel723	pixel724	pixel725	pixel726	pixel727	pixel728	pixel729	pixel730	pixel731	pixel732	pixel733	pixel734	pixel735	pixel736	pixel737	pixel738	pixel739	pixel740	pixel741	pixel742	pixel743	pixel744	pixel745	pixel746	pixel747	pixel748	pixel749	pixel750	pixel751	pixel752	pixel753	pixel754	pixel755	pixel756	pixel757	pixel758	pixel759	pixel760	pixel761	pixel762	pixel763	pixel764	pixel765	pixel766	pixel767	pixel768	pixel769	pixel770	pixel771	pixel772	pixel773	pixel774	pixel775	pixel776	pixel777	pixel778	pixel779	pixel780	pixel781	pixel782	pixel783	pixel784
0	3	107	118	127	134	139	143	146	150	153	156	158	160	163	165	159	166	168	170	170	171	171	171	172	171	171	170	170	169	111	121	129	135	141	144	148	151	154	157	160	163	164	170	119	152	171	171	170	171	172	172	172	172	172	171	171	170	113	123	131	137	142	145	150	152	155	158	161	163	164	172	105	142	170	171	171	171	172	172	173	173	172	171	171	171	116	125	133	139	143	146	151	153	156	159	162	163	167	167	95	144	171	172	172	172	172	172	173	173	173	172	172	171	117	126	134	140	145	149	153	156	158	161	163	164	175	156	87	154	172	173	173	173	173	173	174	174	174	173	172	172	119	128	136	142	146	150	153	156	159	163	165	164	184	148	89	164	172	174	174	174	174	175	175	174	175	174	173	173	122	130	138	143	147	150	154	158	162	165	166	172	181	128	94	170	173	175	174	175	176	177	177	177	177	175	175	174	122	132	139	145	149	152	156	160	163	165	166	181	172	103	113	175	176	178	178	179	179	179	179	178	179	177	175	174	125	134	141	147	150	153	157	161	164	167	168	184	179	116	126	165	176	179	180	180	181	180	180	180	179	178	177	176	128	135	142	148	152	154	158	162	165	168	170	187	180	156	161	124	143	179	178	178	181	182	181	180	181	180	179	179	129	136	144	150	153	155	159	163	166	169	172	187	184	153	102	117	110	175	169	154	182	183	183	182	182	181	181	179	131	138	145	150	155	157	161	165	168	174	190	189	175	146	94	97	113	151	158	129	184	184	184	184	183	183	182	180	131	139	146	151	155	159	163	167	175	182	179	171	159	114	102	89	121	136	136	96	172	186	186	185	185	184	182	181	131	140	147	154	157	160	164	179	186	191	187	180	157	100	88	84	108	111	126	90	120	186	187	187	186	185	184	182	133	141	149	155	158	160	174	201	189	165	151	143	146	120	87	78	87	76	108	98	96	181	188	187	186	186	185	183	133	141	150	156	160	161	179	197	174	135	99	72	95	134	97	72	74	68	116	105	108	187	189	187	187	186	186	185	134	143	151	156	161	163	179	194	156	110	74	42	52	139	94	67	75	75	118	106	129	189	191	190	188	188	187	186	135	144	152	158	163	163	177	193	161	122	84	43	71	134	81	57	71	88	112	98	157	193	193	192	190	190	189	188	136	144	152	158	162	163	176	192	164	128	98	62	60	100	71	76	96	101	105	95	174	195	194	194	194	193	191	190	137	145	152	159	164	165	178	191	164	135	113	82	59	87	98	111	120	108	97	108	190	196	195	195	194	193	193	192	139	146	154	160	164	165	175	186	163	139	112	85	67	102	126	133	126	105	104	176	197	198	197	196	195	195	194	193	138	147	155	161	165	167	172	186	163	137	107	87	76	106	122	125	117	96	156	199	199	200	198	196	196	195	195	194	139	148	156	163	166	168	172	180	158	131	108	99	86	108	118	116	103	107	191	202	201	200	200	200	199	197	198	196	140	149	157	164	168	167	177	178	155	131	118	105	87	100	106	100	96	164	202	202	202	202	202	201	200	199	199	198	140	150	157	165	167	170	181	175	152	130	115	98	82	85	90	99	165	202	203	204	203	203	202	202	201	201	200	200	142	150	159	165	170	191	173	157	144	119	97	84	79	79	91	172	202	203	203	205	204	204	204	203	202	202	201	200	142	151	160	165	188	190	187	150	119	109	85	79	79	78	137	203	205	206	206	207	207	206	206	204	205	204	203	202	142	151	160	172	196	188	188	190	135	96	86	77	77	79	176	205	207	207	207	207	207	207	206	206	206	204	203	202
1	6	155	157	156	156	156	157	156	158	158	157	158	156	154	154	153	152	151	149	149	148	147	146	144	142	143	138	92	108	158	159	159	159	160	160	160	160	160	160	160	159	158	157	155	154	153	152	151	150	149	149	147	147	146	142	116	143	161	161	161	161	162	161	162	162	162	162	161	161	161	160	159	158	156	155	154	153	152	152	151	150	147	147	125	140	165	164	164	165	165	165	165	165	164	164	164	165	163	163	162	161	159	159	158	156	156	155	152	153	154	151	124	126	166	167	166	167	167	166	167	167	167	167	166	167	165	165	164	163	162	162	161	160	156	151	154	176	145	122	144	100	168	169	168	169	169	168	169	170	170	170	169	168	167	166	167	165	162	159	159	156	151	165	171	146	94	130	159	111	171	171	170	171	171	171	172	171	171	171	172	169	169	170	166	165	160	157	170	177	171	153	124	96	125	157	155	146	172	172	172	173	173	173	173	173	173	173	174	174	171	167	169	175	171	164	165	157	129	112	121	148	164	158	155	152	175	174	174	174	175	174	174	174	174	177	178	174	170	178	182	171	154	127	120	126	138	159	168	165	162	161	158	157	176	176	176	176	177	176	176	177	177	175	169	170	178	169	158	163	139	119	155	171	172	168	165	165	163	162	160	158	177	177	177	178	177	178	178	177	171	159	167	173	157	142	163	152	133	167	177	171	170	170	168	167	166	164	161	159	178	178	179	179	180	178	164	141	137	145	150	141	134	150	154	151	177	181	175	172	173	172	170	167	167	165	163	161	180	179	180	182	180	180	170	156	151	148	151	154	153	153	148	153	147	140	171	176	173	173	171	170	168	167	165	163	182	181	181	182	179	164	149	156	159	153	153	166	173	169	169	163	151	105	141	182	174	175	173	171	171	168	166	165	183	183	183	182	171	159	130	125	135	134	130	137	146	147	164	165	147	103	151	182	176	176	175	173	172	170	167	166	184	185	185	176	174	163	147	145	142	141	141	133	125	125	135	135	112	105	181	179	176	177	175	174	173	171	169	166	185	186	182	170	161	132	125	134	130	144	157	159	152	141	132	121	72	142	176	175	182	177	177	177	175	172	169	168	186	186	173	168	159	128	115	119	109	111	140	154	156	153	140	118	64	67	121	148	160	181	177	177	176	173	169	177	189	178	165	173	163	138	128	128	124	117	111	106	118	139	133	93	40	53	109	146	119	174	179	176	175	174	177	168	186	168	169	169	155	151	145	139	135	130	121	112	104	95	101	61	39	71	99	114	103	177	180	178	178	176	130	171	168	166	163	163	158	149	139	137	138	132	122	116	107	72	66	57	55	63	77	95	155	189	186	177	158	115	86	159	162	162	159	168	170	135	106	97	82	83	103	111	87	68	65	54	89	144	155	173	182	157	165	147	109	134	153	145	165	156	162	169	151	101	73	55	54	65	94	98	71	64	53	114	189	183	177	159	147	142	149	126	160	172	130	92	164	169	171	155	114	82	69	52	62	75	91	82	69	62	139	191	154	120	118	137	147	163	145	159	180	126	87	88	162	170	162	135	98	79	66	58	67	68	66	64	79	146	189	148	132	136	133	144	154	184	139	130	121	93	102	100	162	159	145	112	85	75	68	65	64	62	79	123	192	198	183	126	81	123	137	129	154	217	133	87	87	91	101	94	153	139	115	89	77	72	65	77	106	137	174	185	146	121	111	112	100	78	120	157	168	107	99	121	133	97	95	120	135	116	95	79	69	86	139	173	200	185	175	198	124	118	94	140	133	84	69	149	128	87	94	163	175	103	135	149
2	2	187	188	188	187	187	186	187	188	187	186	185	185	185	184	184	184	181	181	179	179	179	178	178	109	52	66	77	83	188	189	189	188	188	189	188	188	188	188	187	185	185	187	182	177	182	182	182	180	180	179	180	135	67	73	73	71	190	190	190	191	190	190	189	189	189	188	189	188	192	184	144	103	144	142	138	186	182	180	182	163	81	74	68	61	191	193	192	192	192	191	191	191	191	195	200	189	165	127	98	71	85	94	86	165	184	182	182	175	87	61	51	56	192	193	194	193	193	193	194	191	202	208	193	130	95	78	69	62	69	72	69	83	179	184	183	184	116	43	38	56	193	193	194	195	195	195	195	196	209	193	144	83	58	61	62	52	60	65	66	70	176	187	184	185	158	45	35	45	194	194	195	196	196	197	195	208	212	133	86	67	52	52	60	61	63	73	91	150	187	187	185	183	175	112	83	55	195	196	195	198	198	198	194	219	193	106	70	68	64	60	63	71	150	174	187	191	187	186	185	185	179	122	145	140	195	197	198	199	200	198	202	224	172	103	69	68	66	60	94	163	195	193	190	190	189	189	187	189	170	89	169	171	198	200	200	200	200	199	215	210	146	84	60	60	61	66	168	201	193	192	191	190	189	189	188	189	169	110	182	143	199	200	201	201	200	203	224	197	142	93	74	68	59	70	177	199	195	194	193	192	191	189	189	189	182	152	130	102	201	201	202	202	200	215	229	186	131	93	82	80	68	81	195	196	195	195	195	193	192	192	191	189	189	183	131	130	201	202	202	203	202	230	222	168	118	87	80	78	75	110	202	197	197	196	195	194	194	193	192	191	190	185	169	161	202	202	203	202	207	237	210	158	108	81	76	76	75	116	205	197	198	198	196	195	195	194	193	191	189	186	174	182	202	203	205	200	218	238	202	151	105	82	79	80	75	129	206	198	199	198	197	196	196	194	193	192	190	189	184	166	204	204	207	202	234	228	186	141	97	80	80	79	68	136	209	198	199	199	198	197	198	197	196	192	192	191	190	158	206	206	202	215	240	217	174	130	91	78	74	71	70	83	192	203	200	200	201	200	191	177	164	151	144	164	190	187	206	207	199	229	234	204	160	119	89	75	66	69	73	69	121	212	204	203	189	164	151	151	146	138	119	91	182	191	208	205	206	238	225	190	149	113	89	70	62	68	73	75	74	156	179	161	147	147	155	151	133	112	117	123	184	189	207	198	224	237	218	181	139	107	85	63	62	75	80	82	83	80	111	136	157	158	140	109	103	154	190	192	190	190	199	209	238	232	209	173	137	100	80	58	73	90	97	102	99	100	117	139	145	122	95	94	175	199	195	193	193	190	200	233	237	224	201	167	129	96	80	61	86	98	106	112	107	107	114	115	103	115	153	187	199	195	194	192	190	190	228	236	226	214	194	160	120	92	78	70	95	104	107	111	103	94	83	100	158	197	202	200	197	195	194	192	190	189	227	228	220	206	183	148	106	90	78	83	103	110	106	95	85	77	121	189	205	202	200	201	198	196	195	192	190	190	219	216	204	182	160	127	96	87	77	89	100	104	94	72	103	174	204	205	203	201	200	201	199	197	195	193	192	191	212	198	175	158	136	103	85	76	81	89	92	88	69	108	195	208	204	203	203	201	200	200	199	196	195	195	193	192	202	179	152	140	118	85	75	78	82	77	75	87	142	203	208	205	203	204	203	201	200	200	199	198	196	195	194	193	198	166	132	114	89	74	79	77	74	78	132	188	210	209	206	205	204	203	202	201	200	199	198	199	198	195	194	195
3	2	211	211	212	212	211	210	211	210	210	211	209	207	208	207	206	203	202	201	200	198	197	195	192	197	171	51	52	54	212	213	215	215	212	212	213	212	212	211	211	209	208	209	206	204	203	202	201	200	199	197	193	204	149	44	49	46	215	217	218	217	216	216	217	214	213	212	212	211	210	211	208	206	206	204	204	202	202	200	194	205	120	52	41	45	218	218	218	218	218	218	218	216	216	215	213	212	213	211	209	208	209	208	208	208	207	202	198	201	90	46	44	34	219	218	220	221	220	220	218	217	219	217	215	214	214	211	201	187	186	182	179	183	192	204	204	196	63	56	49	36	221	221	221	222	222	222	220	220	219	218	217	214	213	212	198	193	186	178	164	150	144	153	192	203	79	51	35	33	224	222	223	223	223	223	220	221	220	219	218	211	208	214	197	176	200	165	145	179	155	141	136	167	93	48	33	32	225	225	225	224	223	223	223	222	221	223	217	210	210	214	155	82	119	104	81	148	158	146	100	89	69	41	38	29	225	226	226	225	226	225	224	223	223	215	216	212	175	151	110	71	63	61	61	84	110	102	80	78	74	50	48	42	226	226	226	226	226	226	226	224	219	217	228	197	126	81	71	70	62	51	60	59	68	75	68	69	91	141	135	60	227	228	228	227	227	227	228	223	222	235	223	174	127	96	60	58	65	85	137	136	185	189	154	155	161	197	182	104	228	229	229	230	228	229	222	224	228	219	183	138	109	93	69	62	60	171	233	222	217	216	219	213	170	175	120	121	230	231	231	230	232	225	223	242	225	205	167	102	82	81	73	62	143	221	215	216	215	211	211	210	185	166	108	168	231	232	232	234	227	225	248	241	213	201	164	108	68	73	72	177	229	219	218	219	218	216	215	214	198	181	156	152	233	233	235	230	226	246	243	224	208	181	132	101	82	58	131	237	219	222	222	220	217	216	216	215	208	182	184	167	235	236	234	226	250	250	230	218	201	162	124	93	62	82	214	228	223	224	225	223	219	217	216	215	214	196	174	181	235	237	233	248	255	244	222	209	182	148	116	82	50	126	246	222	226	226	226	225	219	219	222	213	213	217	180	122	237	234	245	255	252	232	212	198	171	129	98	66	66	68	202	234	224	226	226	223	226	216	182	162	151	187	218	84	233	244	255	247	238	223	202	186	155	110	84	61	73	64	85	225	227	223	228	237	206	145	144	164	111	139	227	163	241	255	252	237	225	209	190	173	135	102	77	76	88	92	67	152	245	231	206	170	130	138	160	121	128	210	211	215	228	255	249	225	216	198	185	162	123	100	82	92	100	98	94	81	147	144	106	94	104	144	114	106	220	215	213	210	90	146	207	193	183	193	175	148	120	94	83	99	102	99	97	89	78	87	98	122	111	117	61	177	226	215	215	211	74	63	80	119	134	134	136	117	90	77	82	97	97	97	93	89	86	106	109	117	102	63	91	224	218	218	215	212	71	72	65	65	65	71	75	57	54	66	70	83	88	88	84	89	90	95	87	77	89	144	210	224	219	219	217	214	67	66	63	65	58	29	34	43	46	53	52	66	79	74	67	64	57	70	115	167	216	236	228	223	221	220	219	217	65	62	58	55	63	44	11	22	24	28	34	49	46	62	95	109	141	202	237	240	231	226	226	224	222	220	219	217	63	56	52	52	59	56	17	16	20	17	17	14	120	217	237	244	247	242	233	231	230	229	227	225	223	221	220	216	58	51	49	50	57	60	17	15	18	17	19	1	159	255	237	239	237	236	235	234	233	231	230	226	225	222	229	163
4	13	164	167	170	172	176	179	180	184	185	186	188	189	189	190	191	189	190	190	187	190	192	193	191	191	192	192	194	194	166	169	172	174	177	180	182	185	186	187	190	191	190	191	192	192	194	182	152	146	189	195	194	193	193	194	195	195	167	170	173	176	178	181	183	186	187	188	191	193	192	191	188	193	206	182	136	92	172	196	196	197	195	197	197	196	170	172	175	177	180	184	186	188	188	191	192	193	197	183	153	153	196	178	135	82	140	142	147	176	199	200	199	197	171	173	176	179	182	185	187	189	190	193	193	195	214	190	144	117	178	173	132	77	113	136	105	104	191	201	200	199	172	174	177	181	184	187	188	190	193	193	193	182	187	191	163	121	172	166	119	80	156	159	104	76	169	203	200	200	173	175	179	182	185	188	190	192	193	195	197	158	120	132	165	118	164	183	117	106	183	154	107	74	166	205	202	202	174	177	180	183	187	189	192	193	194	203	200	163	126	97	146	116	159	191	122	123	183	150	102	76	177	204	203	203	175	179	181	185	188	190	193	193	201	193	192	177	137	95	124	125	104	119	88	120	197	160	97	84	190	204	204	205	177	180	183	187	189	192	194	196	203	176	172	175	135	92	101	129	77	27	64	133	174	133	74	98	201	206	206	206	178	182	185	187	189	192	194	201	202	178	153	166	135	87	86	121	88	27	69	154	158	114	81	132	208	207	208	208	178	181	184	187	190	194	194	208	204	176	139	165	131	88	79	112	95	63	127	162	163	147	122	115	198	208	209	209	178	181	185	188	191	195	196	210	203	172	136	150	127	89	76	131	118	118	188	177	153	133	113	88	168	212	210	210	180	182	185	189	192	195	197	213	202	173	142	135	128	109	76	151	146	168	194	179	152	119	98	84	171	212	210	211	181	182	186	189	193	196	199	213	202	180	159	133	116	111	70	149	183	204	193	170	143	110	89	93	192	213	211	211	181	184	187	190	194	196	200	214	203	183	166	149	119	104	109	188	205	209	189	160	133	102	85	108	206	213	213	212	182	185	188	191	194	196	200	211	203	185	171	164	140	122	127	187	206	201	173	142	119	95	85	147	214	214	215	214	181	185	187	190	193	196	199	204	200	190	176	169	148	127	124	183	205	189	157	128	108	89	103	196	214	214	216	215	181	184	187	191	193	196	197	200	199	192	176	171	154	131	131	173	199	174	145	119	99	82	143	214	213	214	215	214	181	184	187	191	194	196	198	200	202	194	177	167	151	131	133	168	176	153	132	109	92	89	181	213	213	213	213	214	182	185	188	192	194	196	198	200	203	191	172	162	142	124	137	161	150	137	117	98	87	123	207	213	214	214	214	214	184	186	189	192	194	196	198	197	203	182	165	151	129	123	143	151	134	127	107	92	94	177	214	214	214	214	215	215	184	185	189	192	195	197	194	201	202	178	166	147	132	134	150	145	130	116	100	88	145	209	214	214	215	215	216	216	184	186	189	193	196	198	194	209	207	184	175	148	137	148	153	133	122	100	87	110	195	215	215	214	215	215	216	216	180	184	187	191	194	196	192	206	202	186	181	152	146	155	143	121	106	88	82	161	213	214	216	215	216	216	216	217	130	134	139	143	147	146	173	200	187	178	174	150	143	149	138	108	94	81	94	178	198	201	204	206	208	209	211	211	99	101	100	100	100	97	163	200	179	161	150	138	138	151	132	97	90	77	88	117	123	127	129	134	145	152	156	179	105	106	105	104	104	104	175	199	178	152	136	130	136	150	118	92	85	76	92	105	105	108	133	163	157	163	164	179

Xy_original.info(verbose=True)

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 27455 entries, 0 to 27454
Data columns (total 785 columns):
 #   Column    Dtype
---  ------    -----
 0   label     int64
 1   pixel1    int64
 2   pixel2    int64
 3   pixel3    int64
 4   pixel4    int64
 5   pixel5    int64
 6   pixel6    int64
 7   pixel7    int64
 8   pixel8    int64
 9   pixel9    int64
 10  pixel10   int64
 11  pixel11   int64
 12  pixel12   int64
 13  pixel13   int64
 14  pixel14   int64
 15  pixel15   int64
 16  pixel16   int64
 17  pixel17   int64
 18  pixel18   int64
 19  pixel19   int64
 20  pixel20   int64
 21  pixel21   int64
 22  pixel22   int64
 23  pixel23   int64
 24  pixel24   int64
 25  pixel25   int64
 26  pixel26   int64
 27  pixel27   int64
 28  pixel28   int64
 29  pixel29   int64
 30  pixel30   int64
 31  pixel31   int64
 32  pixel32   int64
 33  pixel33   int64
 34  pixel34   int64
 35  pixel35   int64
 36  pixel36   int64
 37  pixel37   int64
 38  pixel38   int64
 39  pixel39   int64
 40  pixel40   int64
 41  pixel41   int64
 42  pixel42   int64
 43  pixel43   int64
 44  pixel44   int64
 45  pixel45   int64
 46  pixel46   int64
 47  pixel47   int64
 48  pixel48   int64
 49  pixel49   int64
 50  pixel50   int64
 51  pixel51   int64
 52  pixel52   int64
 53  pixel53   int64
 54  pixel54   int64
 55  pixel55   int64
 56  pixel56   int64
 57  pixel57   int64
 58  pixel58   int64
 59  pixel59   int64
 60  pixel60   int64
 61  pixel61   int64
 62  pixel62   int64
 63  pixel63   int64
 64  pixel64   int64
 65  pixel65   int64
 66  pixel66   int64
 67  pixel67   int64
 68  pixel68   int64
 69  pixel69   int64
 70  pixel70   int64
 71  pixel71   int64
 72  pixel72   int64
 73  pixel73   int64
 74  pixel74   int64
 75  pixel75   int64
 76  pixel76   int64
 77  pixel77   int64
 78  pixel78   int64
 79  pixel79   int64
 80  pixel80   int64
 81  pixel81   int64
 82  pixel82   int64
 83  pixel83   int64
 84  pixel84   int64
 85  pixel85   int64
 86  pixel86   int64
 87  pixel87   int64
 88  pixel88   int64
 89  pixel89   int64
 90  pixel90   int64
 91  pixel91   int64
 92  pixel92   int64
 93  pixel93   int64
 94  pixel94   int64
 95  pixel95   int64
 96  pixel96   int64
 97  pixel97   int64
 98  pixel98   int64
 99  pixel99   int64
 100 pixel100  int64
 101 pixel101  int64
 102 pixel102  int64
 103 pixel103  int64
 104 pixel104  int64
 105 pixel105  int64
 106 pixel106  int64
 107 pixel107  int64
 108 pixel108  int64
 109 pixel109  int64
 110 pixel110  int64
 111 pixel111  int64
 112 pixel112  int64
 113 pixel113  int64
 114 pixel114  int64
 115 pixel115  int64
 116 pixel116  int64
 117 pixel117  int64
 118 pixel118  int64
 119 pixel119  int64
 120 pixel120  int64
 121 pixel121  int64
 122 pixel122  int64
 123 pixel123  int64
 124 pixel124  int64
 125 pixel125  int64
 126 pixel126  int64
 127 pixel127  int64
 128 pixel128  int64
 129 pixel129  int64
 130 pixel130  int64
 131 pixel131  int64
 132 pixel132  int64
 133 pixel133  int64
 134 pixel134  int64
 135 pixel135  int64
 136 pixel136  int64
 137 pixel137  int64
 138 pixel138  int64
 139 pixel139  int64
 140 pixel140  int64
 141 pixel141  int64
 142 pixel142  int64
 143 pixel143  int64
 144 pixel144  int64
 145 pixel145  int64
 146 pixel146  int64
 147 pixel147  int64
 148 pixel148  int64
 149 pixel149  int64
 150 pixel150  int64
 151 pixel151  int64
 152 pixel152  int64
 153 pixel153  int64
 154 pixel154  int64
 155 pixel155  int64
 156 pixel156  int64
 157 pixel157  int64
 158 pixel158  int64
 159 pixel159  int64
 160 pixel160  int64
 161 pixel161  int64
 162 pixel162  int64
 163 pixel163  int64
 164 pixel164  int64
 165 pixel165  int64
 166 pixel166  int64
 167 pixel167  int64
 168 pixel168  int64
 169 pixel169  int64
 170 pixel170  int64
 171 pixel171  int64
 172 pixel172  int64
 173 pixel173  int64
 174 pixel174  int64
 175 pixel175  int64
 176 pixel176  int64
 177 pixel177  int64
 178 pixel178  int64
 179 pixel179  int64
 180 pixel180  int64
 181 pixel181  int64
 182 pixel182  int64
 183 pixel183  int64
 184 pixel184  int64
 185 pixel185  int64
 186 pixel186  int64
 187 pixel187  int64
 188 pixel188  int64
 189 pixel189  int64
 190 pixel190  int64
 191 pixel191  int64
 192 pixel192  int64
 193 pixel193  int64
 194 pixel194  int64
 195 pixel195  int64
 196 pixel196  int64
 197 pixel197  int64
 198 pixel198  int64
 199 pixel199  int64
 200 pixel200  int64
 201 pixel201  int64
 202 pixel202  int64
 203 pixel203  int64
 204 pixel204  int64
 205 pixel205  int64
 206 pixel206  int64
 207 pixel207  int64
 208 pixel208  int64
 209 pixel209  int64
 210 pixel210  int64
 211 pixel211  int64
 212 pixel212  int64
 213 pixel213  int64
 214 pixel214  int64
 215 pixel215  int64
 216 pixel216  int64
 217 pixel217  int64
 218 pixel218  int64
 219 pixel219  int64
 220 pixel220  int64
 221 pixel221  int64
 222 pixel222  int64
 223 pixel223  int64
 224 pixel224  int64
 225 pixel225  int64
 226 pixel226  int64
 227 pixel227  int64
 228 pixel228  int64
 229 pixel229  int64
 230 pixel230  int64
 231 pixel231  int64
 232 pixel232  int64
 233 pixel233  int64
 234 pixel234  int64
 235 pixel235  int64
 236 pixel236  int64
 237 pixel237  int64
 238 pixel238  int64
 239 pixel239  int64
 240 pixel240  int64
 241 pixel241  int64
 242 pixel242  int64
 243 pixel243  int64
 244 pixel244  int64
 245 pixel245  int64
 246 pixel246  int64
 247 pixel247  int64
 248 pixel248  int64
 249 pixel249  int64
 250 pixel250  int64
 251 pixel251  int64
 252 pixel252  int64
 253 pixel253  int64
 254 pixel254  int64
 255 pixel255  int64
 256 pixel256  int64
 257 pixel257  int64
 258 pixel258  int64
 259 pixel259  int64
 260 pixel260  int64
 261 pixel261  int64
 262 pixel262  int64
 263 pixel263  int64
 264 pixel264  int64
 265 pixel265  int64
 266 pixel266  int64
 267 pixel267  int64
 268 pixel268  int64
 269 pixel269  int64
 270 pixel270  int64
 271 pixel271  int64
 272 pixel272  int64
 273 pixel273  int64
 274 pixel274  int64
 275 pixel275  int64
 276 pixel276  int64
 277 pixel277  int64
 278 pixel278  int64
 279 pixel279  int64
 280 pixel280  int64
 281 pixel281  int64
 282 pixel282  int64
 283 pixel283  int64
 284 pixel284  int64
 285 pixel285  int64
 286 pixel286  int64
 287 pixel287  int64
 288 pixel288  int64
 289 pixel289  int64
 290 pixel290  int64
 291 pixel291  int64
 292 pixel292  int64
 293 pixel293  int64
 294 pixel294  int64
 295 pixel295  int64
 296 pixel296  int64
 297 pixel297  int64
 298 pixel298  int64
 299 pixel299  int64
 300 pixel300  int64
 301 pixel301  int64
 302 pixel302  int64
 303 pixel303  int64
 304 pixel304  int64
 305 pixel305  int64
 306 pixel306  int64
 307 pixel307  int64
 308 pixel308  int64
 309 pixel309  int64
 310 pixel310  int64
 311 pixel311  int64
 312 pixel312  int64
 313 pixel313  int64
 314 pixel314  int64
 315 pixel315  int64
 316 pixel316  int64
 317 pixel317  int64
 318 pixel318  int64
 319 pixel319  int64
 320 pixel320  int64
 321 pixel321  int64
 322 pixel322  int64
 323 pixel323  int64
 324 pixel324  int64
 325 pixel325  int64
 326 pixel326  int64
 327 pixel327  int64
 328 pixel328  int64
 329 pixel329  int64
 330 pixel330  int64
 331 pixel331  int64
 332 pixel332  int64
 333 pixel333  int64
 334 pixel334  int64
 335 pixel335  int64
 336 pixel336  int64
 337 pixel337  int64
 338 pixel338  int64
 339 pixel339  int64
 340 pixel340  int64
 341 pixel341  int64
 342 pixel342  int64
 343 pixel343  int64
 344 pixel344  int64
 345 pixel345  int64
 346 pixel346  int64
 347 pixel347  int64
 348 pixel348  int64
 349 pixel349  int64
 350 pixel350  int64
 351 pixel351  int64
 352 pixel352  int64
 353 pixel353  int64
 354 pixel354  int64
 355 pixel355  int64
 356 pixel356  int64
 357 pixel357  int64
 358 pixel358  int64
 359 pixel359  int64
 360 pixel360  int64
 361 pixel361  int64
 362 pixel362  int64
 363 pixel363  int64
 364 pixel364  int64
 365 pixel365  int64
 366 pixel366  int64
 367 pixel367  int64
 368 pixel368  int64
 369 pixel369  int64
 370 pixel370  int64
 371 pixel371  int64
 372 pixel372  int64
 373 pixel373  int64
 374 pixel374  int64
 375 pixel375  int64
 376 pixel376  int64
 377 pixel377  int64
 378 pixel378  int64
 379 pixel379  int64
 380 pixel380  int64
 381 pixel381  int64
 382 pixel382  int64
 383 pixel383  int64
 384 pixel384  int64
 385 pixel385  int64
 386 pixel386  int64
 387 pixel387  int64
 388 pixel388  int64
 389 pixel389  int64
 390 pixel390  int64
 391 pixel391  int64
 392 pixel392  int64
 393 pixel393  int64
 394 pixel394  int64
 395 pixel395  int64
 396 pixel396  int64
 397 pixel397  int64
 398 pixel398  int64
 399 pixel399  int64
 400 pixel400  int64
 401 pixel401  int64
 402 pixel402  int64
 403 pixel403  int64
 404 pixel404  int64
 405 pixel405  int64
 406 pixel406  int64
 407 pixel407  int64
 408 pixel408  int64
 409 pixel409  int64
 410 pixel410  int64
 411 pixel411  int64
 412 pixel412  int64
 413 pixel413  int64
 414 pixel414  int64
 415 pixel415  int64
 416 pixel416  int64
 417 pixel417  int64
 418 pixel418  int64
 419 pixel419  int64
 420 pixel420  int64
 421 pixel421  int64
 422 pixel422  int64
 423 pixel423  int64
 424 pixel424  int64
 425 pixel425  int64
 426 pixel426  int64
 427 pixel427  int64
 428 pixel428  int64
 429 pixel429  int64
 430 pixel430  int64
 431 pixel431  int64
 432 pixel432  int64
 433 pixel433  int64
 434 pixel434  int64
 435 pixel435  int64
 436 pixel436  int64
 437 pixel437  int64
 438 pixel438  int64
 439 pixel439  int64
 440 pixel440  int64
 441 pixel441  int64
 442 pixel442  int64
 443 pixel443  int64
 444 pixel444  int64
 445 pixel445  int64
 446 pixel446  int64
 447 pixel447  int64
 448 pixel448  int64
 449 pixel449  int64
 450 pixel450  int64
 451 pixel451  int64
 452 pixel452  int64
 453 pixel453  int64
 454 pixel454  int64
 455 pixel455  int64
 456 pixel456  int64
 457 pixel457  int64
 458 pixel458  int64
 459 pixel459  int64
 460 pixel460  int64
 461 pixel461  int64
 462 pixel462  int64
 463 pixel463  int64
 464 pixel464  int64
 465 pixel465  int64
 466 pixel466  int64
 467 pixel467  int64
 468 pixel468  int64
 469 pixel469  int64
 470 pixel470  int64
 471 pixel471  int64
 472 pixel472  int64
 473 pixel473  int64
 474 pixel474  int64
 475 pixel475  int64
 476 pixel476  int64
 477 pixel477  int64
 478 pixel478  int64
 479 pixel479  int64
 480 pixel480  int64
 481 pixel481  int64
 482 pixel482  int64
 483 pixel483  int64
 484 pixel484  int64
 485 pixel485  int64
 486 pixel486  int64
 487 pixel487  int64
 488 pixel488  int64
 489 pixel489  int64
 490 pixel490  int64
 491 pixel491  int64
 492 pixel492  int64
 493 pixel493  int64
 494 pixel494  int64
 495 pixel495  int64
 496 pixel496  int64
 497 pixel497  int64
 498 pixel498  int64
 499 pixel499  int64
 500 pixel500  int64
 501 pixel501  int64
 502 pixel502  int64
 503 pixel503  int64
 504 pixel504  int64
 505 pixel505  int64
 506 pixel506  int64
 507 pixel507  int64
 508 pixel508  int64
 509 pixel509  int64
 510 pixel510  int64
 511 pixel511  int64
 512 pixel512  int64
 513 pixel513  int64
 514 pixel514  int64
 515 pixel515  int64
 516 pixel516  int64
 517 pixel517  int64
 518 pixel518  int64
 519 pixel519  int64
 520 pixel520  int64
 521 pixel521  int64
 522 pixel522  int64
 523 pixel523  int64
 524 pixel524  int64
 525 pixel525  int64
 526 pixel526  int64
 527 pixel527  int64
 528 pixel528  int64
 529 pixel529  int64
 530 pixel530  int64
 531 pixel531  int64
 532 pixel532  int64
 533 pixel533  int64
 534 pixel534  int64
 535 pixel535  int64
 536 pixel536  int64
 537 pixel537  int64
 538 pixel538  int64
 539 pixel539  int64
 540 pixel540  int64
 541 pixel541  int64
 542 pixel542  int64
 543 pixel543  int64
 544 pixel544  int64
 545 pixel545  int64
 546 pixel546  int64
 547 pixel547  int64
 548 pixel548  int64
 549 pixel549  int64
 550 pixel550  int64
 551 pixel551  int64
 552 pixel552  int64
 553 pixel553  int64
 554 pixel554  int64
 555 pixel555  int64
 556 pixel556  int64
 557 pixel557  int64
 558 pixel558  int64
 559 pixel559  int64
 560 pixel560  int64
 561 pixel561  int64
 562 pixel562  int64
 563 pixel563  int64
 564 pixel564  int64
 565 pixel565  int64
 566 pixel566  int64
 567 pixel567  int64
 568 pixel568  int64
 569 pixel569  int64
 570 pixel570  int64
 571 pixel571  int64
 572 pixel572  int64
 573 pixel573  int64
 574 pixel574  int64
 575 pixel575  int64
 576 pixel576  int64
 577 pixel577  int64
 578 pixel578  int64
 579 pixel579  int64
 580 pixel580  int64
 581 pixel581  int64
 582 pixel582  int64
 583 pixel583  int64
 584 pixel584  int64
 585 pixel585  int64
 586 pixel586  int64
 587 pixel587  int64
 588 pixel588  int64
 589 pixel589  int64
 590 pixel590  int64
 591 pixel591  int64
 592 pixel592  int64
 593 pixel593  int64
 594 pixel594  int64
 595 pixel595  int64
 596 pixel596  int64
 597 pixel597  int64
 598 pixel598  int64
 599 pixel599  int64
 600 pixel600  int64
 601 pixel601  int64
 602 pixel602  int64
 603 pixel603  int64
 604 pixel604  int64
 605 pixel605  int64
 606 pixel606  int64
 607 pixel607  int64
 608 pixel608  int64
 609 pixel609  int64
 610 pixel610  int64
 611 pixel611  int64
 612 pixel612  int64
 613 pixel613  int64
 614 pixel614  int64
 615 pixel615  int64
 616 pixel616  int64
 617 pixel617  int64
 618 pixel618  int64
 619 pixel619  int64
 620 pixel620  int64
 621 pixel621  int64
 622 pixel622  int64
 623 pixel623  int64
 624 pixel624  int64
 625 pixel625  int64
 626 pixel626  int64
 627 pixel627  int64
 628 pixel628  int64
 629 pixel629  int64
 630 pixel630  int64
 631 pixel631  int64
 632 pixel632  int64
 633 pixel633  int64
 634 pixel634  int64
 635 pixel635  int64
 636 pixel636  int64
 637 pixel637  int64
 638 pixel638  int64
 639 pixel639  int64
 640 pixel640  int64
 641 pixel641  int64
 642 pixel642  int64
 643 pixel643  int64
 644 pixel644  int64
 645 pixel645  int64
 646 pixel646  int64
 647 pixel647  int64
 648 pixel648  int64
 649 pixel649  int64
 650 pixel650  int64
 651 pixel651  int64
 652 pixel652  int64
 653 pixel653  int64
 654 pixel654  int64
 655 pixel655  int64
 656 pixel656  int64
 657 pixel657  int64
 658 pixel658  int64
 659 pixel659  int64
 660 pixel660  int64
 661 pixel661  int64
 662 pixel662  int64
 663 pixel663  int64
 664 pixel664  int64
 665 pixel665  int64
 666 pixel666  int64
 667 pixel667  int64
 668 pixel668  int64
 669 pixel669  int64
 670 pixel670  int64
 671 pixel671  int64
 672 pixel672  int64
 673 pixel673  int64
 674 pixel674  int64
 675 pixel675  int64
 676 pixel676  int64
 677 pixel677  int64
 678 pixel678  int64
 679 pixel679  int64
 680 pixel680  int64
 681 pixel681  int64
 682 pixel682  int64
 683 pixel683  int64
 684 pixel684  int64
 685 pixel685  int64
 686 pixel686  int64
 687 pixel687  int64
 688 pixel688  int64
 689 pixel689  int64
 690 pixel690  int64
 691 pixel691  int64
 692 pixel692  int64
 693 pixel693  int64
 694 pixel694  int64
 695 pixel695  int64
 696 pixel696  int64
 697 pixel697  int64
 698 pixel698  int64
 699 pixel699  int64
 700 pixel700  int64
 701 pixel701  int64
 702 pixel702  int64
 703 pixel703  int64
 704 pixel704  int64
 705 pixel705  int64
 706 pixel706  int64
 707 pixel707  int64
 708 pixel708  int64
 709 pixel709  int64
 710 pixel710  int64
 711 pixel711  int64
 712 pixel712  int64
 713 pixel713  int64
 714 pixel714  int64
 715 pixel715  int64
 716 pixel716  int64
 717 pixel717  int64
 718 pixel718  int64
 719 pixel719  int64
 720 pixel720  int64
 721 pixel721  int64
 722 pixel722  int64
 723 pixel723  int64
 724 pixel724  int64
 725 pixel725  int64
 726 pixel726  int64
 727 pixel727  int64
 728 pixel728  int64
 729 pixel729  int64
 730 pixel730  int64
 731 pixel731  int64
 732 pixel732  int64
 733 pixel733  int64
 734 pixel734  int64
 735 pixel735  int64
 736 pixel736  int64
 737 pixel737  int64
 738 pixel738  int64
 739 pixel739  int64
 740 pixel740  int64
 741 pixel741  int64
 742 pixel742  int64
 743 pixel743  int64
 744 pixel744  int64
 745 pixel745  int64
 746 pixel746  int64
 747 pixel747  int64
 748 pixel748  int64
 749 pixel749  int64
 750 pixel750  int64
 751 pixel751  int64
 752 pixel752  int64
 753 pixel753  int64
 754 pixel754  int64
 755 pixel755  int64
 756 pixel756  int64
 757 pixel757  int64
 758 pixel758  int64
 759 pixel759  int64
 760 pixel760  int64
 761 pixel761  int64
 762 pixel762  int64
 763 pixel763  int64
 764 pixel764  int64
 765 pixel765  int64
 766 pixel766  int64
 767 pixel767  int64
 768 pixel768  int64
 769 pixel769  int64
 770 pixel770  int64
 771 pixel771  int64
 772 pixel772  int64
 773 pixel773  int64
 774 pixel774  int64
 775 pixel775  int64
 776 pixel776  int64
 777 pixel777  int64
 778 pixel778  int64
 779 pixel779  int64
 780 pixel780  int64
 781 pixel781  int64
 782 pixel782  int64
 783 pixel783  int64
 784 pixel784  int64
dtypes: int64(785)
memory usage: 164.4 MB

Xy_original.describe()

	label	pixel1	pixel2	pixel3	pixel4	pixel5	pixel6	pixel7	pixel8	pixel9	pixel10	pixel11	pixel12	pixel13	pixel14	pixel15	pixel16	pixel17	pixel18	pixel19	pixel20	pixel21	pixel22	pixel23	pixel24	pixel25	pixel26	pixel27	pixel28	pixel29	pixel30	pixel31	pixel32	pixel33	pixel34	pixel35	pixel36	pixel37	pixel38	pixel39	pixel40	pixel41	pixel42	pixel43	pixel44	pixel45	pixel46	pixel47	pixel48	pixel49	pixel50	pixel51	pixel52	pixel53	pixel54	pixel55	pixel56	pixel57	pixel58	pixel59	pixel60	pixel61	pixel62	pixel63	pixel64	pixel65	pixel66	pixel67	pixel68	pixel69	pixel70	pixel71	pixel72	pixel73	pixel74	pixel75	pixel76	pixel77	pixel78	pixel79	pixel80	pixel81	pixel82	pixel83	pixel84	pixel85	pixel86	pixel87	pixel88	pixel89	pixel90	pixel91	pixel92	pixel93	pixel94	pixel95	pixel96	pixel97	pixel98	pixel99	pixel100	pixel101	pixel102	pixel103	pixel104	pixel105	pixel106	pixel107	pixel108	pixel109	pixel110	pixel111	pixel112	pixel113	pixel114	pixel115	pixel116	pixel117	pixel118	pixel119	pixel120	pixel121	pixel122	pixel123	pixel124	pixel125	pixel126	pixel127	pixel128	pixel129	pixel130	pixel131	pixel132	pixel133	pixel134	pixel135	pixel136	pixel137	pixel138	pixel139	pixel140	pixel141	pixel142	pixel143	pixel144	pixel145	pixel146	pixel147	pixel148	pixel149	pixel150	pixel151	pixel152	pixel153	pixel154	pixel155	pixel156	pixel157	pixel158	pixel159	pixel160	pixel161	pixel162	pixel163	pixel164	pixel165	pixel166	pixel167	pixel168	pixel169	pixel170	pixel171	pixel172	pixel173	pixel174	pixel175	pixel176	pixel177	pixel178	pixel179	pixel180	pixel181	pixel182	pixel183	pixel184	pixel185	pixel186	pixel187	pixel188	pixel189	pixel190	pixel191	pixel192	pixel193	pixel194	pixel195	pixel196	pixel197	pixel198	pixel199	pixel200	pixel201	pixel202	pixel203	pixel204	pixel205	pixel206	pixel207	pixel208	pixel209	pixel210	pixel211	pixel212	pixel213	pixel214	pixel215	pixel216	pixel217	pixel218	pixel219	pixel220	pixel221	pixel222	pixel223	pixel224	pixel225	pixel226	pixel227	pixel228	pixel229	pixel230	pixel231	pixel232	pixel233	pixel234	pixel235	pixel236	pixel237	pixel238	pixel239	pixel240	pixel241	pixel242	pixel243	pixel244	pixel245	pixel246	pixel247	pixel248	pixel249	pixel250	pixel251	pixel252	pixel253	pixel254	pixel255	pixel256	pixel257	pixel258	pixel259	pixel260	pixel261	pixel262	pixel263	pixel264	pixel265	pixel266	pixel267	pixel268	pixel269	pixel270	pixel271	pixel272	pixel273	pixel274	pixel275	pixel276	pixel277	pixel278	pixel279	pixel280	pixel281	pixel282	pixel283	pixel284	pixel285	pixel286	pixel287	pixel288	pixel289	pixel290	pixel291	pixel292	pixel293	pixel294	pixel295	pixel296	pixel297	pixel298	pixel299	pixel300	pixel301	pixel302	pixel303	pixel304	pixel305	pixel306	pixel307	pixel308	pixel309	pixel310	pixel311	pixel312	pixel313	pixel314	pixel315	pixel316	pixel317	pixel318	pixel319	pixel320	pixel321	pixel322	pixel323	pixel324	pixel325	pixel326	pixel327	pixel328	pixel329	pixel330	pixel331	pixel332	pixel333	pixel334	pixel335	pixel336	pixel337	pixel338	pixel339	pixel340	pixel341	pixel342	pixel343	pixel344	pixel345	pixel346	pixel347	pixel348	pixel349	pixel350	pixel351	pixel352	pixel353	pixel354	pixel355	pixel356	pixel357	pixel358	pixel359	pixel360	pixel361	pixel362	pixel363	pixel364	pixel365	pixel366	pixel367	pixel368	pixel369	pixel370	pixel371	pixel372	pixel373	pixel374	pixel375	pixel376	pixel377	pixel378	pixel379	pixel380	pixel381	pixel382	pixel383	pixel384	pixel385	pixel386	pixel387	pixel388	pixel389	pixel390	pixel391	pixel392	pixel393	pixel394	pixel395	pixel396	pixel397	pixel398	pixel399	pixel400	pixel401	pixel402	pixel403	pixel404	pixel405	pixel406	pixel407	pixel408	pixel409	pixel410	pixel411	pixel412	pixel413	pixel414	pixel415	pixel416	pixel417	pixel418	pixel419	pixel420	pixel421	pixel422	pixel423	pixel424	pixel425	pixel426	pixel427	pixel428	pixel429	pixel430	pixel431	pixel432	pixel433	pixel434	pixel435	pixel436	pixel437	pixel438	pixel439	pixel440	pixel441	pixel442	pixel443	pixel444	pixel445	pixel446	pixel447	pixel448	pixel449	pixel450	pixel451	pixel452	pixel453	pixel454	pixel455	pixel456	pixel457	pixel458	pixel459	pixel460	pixel461	pixel462	pixel463	pixel464	pixel465	pixel466	pixel467	pixel468	pixel469	pixel470	pixel471	pixel472	pixel473	pixel474	pixel475	pixel476	pixel477	pixel478	pixel479	pixel480	pixel481	pixel482	pixel483	pixel484	pixel485	pixel486	pixel487	pixel488	pixel489	pixel490	pixel491	pixel492	pixel493	pixel494	pixel495	pixel496	pixel497	pixel498	pixel499	pixel500	pixel501	pixel502	pixel503	pixel504	pixel505	pixel506	pixel507	pixel508	pixel509	pixel510	pixel511	pixel512	pixel513	pixel514	pixel515	pixel516	pixel517	pixel518	pixel519	pixel520	pixel521	pixel522	pixel523	pixel524	pixel525	pixel526	pixel527	pixel528	pixel529	pixel530	pixel531	pixel532	pixel533	pixel534	pixel535	pixel536	pixel537	pixel538	pixel539	pixel540	pixel541	pixel542	pixel543	pixel544	pixel545	pixel546	pixel547	pixel548	pixel549	pixel550	pixel551	pixel552	pixel553	pixel554	pixel555	pixel556	pixel557	pixel558	pixel559	pixel560	pixel561	pixel562	pixel563	pixel564	pixel565	pixel566	pixel567	pixel568	pixel569	pixel570	pixel571	pixel572	pixel573	pixel574	pixel575	pixel576	pixel577	pixel578	pixel579	pixel580	pixel581	pixel582	pixel583	pixel584	pixel585	pixel586	pixel587	pixel588	pixel589	pixel590	pixel591	pixel592	pixel593	pixel594	pixel595	pixel596	pixel597	pixel598	pixel599	pixel600	pixel601	pixel602	pixel603	pixel604	pixel605	pixel606	pixel607	pixel608	pixel609	pixel610	pixel611	pixel612	pixel613	pixel614	pixel615	pixel616	pixel617	pixel618	pixel619	pixel620	pixel621	pixel622	pixel623	pixel624	pixel625	pixel626	pixel627	pixel628	pixel629	pixel630	pixel631	pixel632	pixel633	pixel634	pixel635	pixel636	pixel637	pixel638	pixel639	pixel640	pixel641	pixel642	pixel643	pixel644	pixel645	pixel646	pixel647	pixel648	pixel649	pixel650	pixel651	pixel652	pixel653	pixel654	pixel655	pixel656	pixel657	pixel658	pixel659	pixel660	pixel661	pixel662	pixel663	pixel664	pixel665	pixel666	pixel667	pixel668	pixel669	pixel670	pixel671	pixel672	pixel673	pixel674	pixel675	pixel676	pixel677	pixel678	pixel679	pixel680	pixel681	pixel682	pixel683	pixel684	pixel685	pixel686	pixel687	pixel688	pixel689	pixel690	pixel691	pixel692	pixel693	pixel694	pixel695	pixel696	pixel697	pixel698	pixel699	pixel700	pixel701	pixel702	pixel703	pixel704	pixel705	pixel706	pixel707	pixel708	pixel709	pixel710	pixel711	pixel712	pixel713	pixel714	pixel715	pixel716	pixel717	pixel718	pixel719	pixel720	pixel721	pixel722	pixel723	pixel724	pixel725	pixel726	pixel727	pixel728	pixel729	pixel730	pixel731	pixel732	pixel733	pixel734	pixel735	pixel736	pixel737	pixel738	pixel739	pixel740	pixel741	pixel742	pixel743	pixel744	pixel745	pixel746	pixel747	pixel748	pixel749	pixel750	pixel751	pixel752	pixel753	pixel754	pixel755	pixel756	pixel757	pixel758	pixel759	pixel760	pixel761	pixel762	pixel763	pixel764	pixel765	pixel766	pixel767	pixel768	pixel769	pixel770	pixel771	pixel772	pixel773	pixel774	pixel775	pixel776	pixel777	pixel778	pixel779	pixel780	pixel781	pixel782	pixel783	pixel784
count	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.00000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.00000	27455.000000	27455.000000	27455.00000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.00000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.00000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.00000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000	27455.000000
mean	12.318813	145.419377	148.500273	151.247714	153.546531	156.210891	158.411255	160.472154	162.339683	163.954799	165.533673	166.685522	167.811983	168.495647	169.310872	169.956948	170.460463	170.716518	170.872701	170.808887	170.481442	169.979749	169.264506	168.144127	166.936660	165.765944	163.620725	161.933600	161.349117	147.146858	150.284502	152.941978	155.415043	158.068986	160.229576	162.345802	164.291167	165.736332	166.991732	168.503187	169.287307	169.497032	170.483555	170.871135	170.719869	170.966746	171.462211	171.149700	171.330905	171.165762	170.522928	169.719286	168.686141	167.347478	165.249026	163.697469	163.000692	149.015261	152.235658	154.769004	157.313094	159.958405	162.161610	164.117137	166.232708	167.487598	168.327445	169.971044	170.829612	170.275068	170.515899	169.761464	168.849317	169.004881	169.285995	169.316846	170.031870	170.758441	170.891131	170.767729	169.811182	168.659188	166.789547	165.502604	164.464615	150.796394	154.049390	156.568494	159.179894	161.803205	163.928647	165.834748	167.930432	169.131743	169.709889	170.810490	171.719177	170.191368	169.667565	167.190603	165.321981	164.602295	163.880932	163.827208	165.756037	167.947332	169.768749	170.402659	170.087161	169.758332	168.298088	167.258641	166.543835	152.493498	155.773302	158.350100	161.159060	163.587179	165.623202	167.475833	169.657294	170.893353	170.830013	170.895647	170.633036	168.574431	167.321726	164.408705	161.673101	160.192169	158.133418	157.576361	160.449353	162.830960	166.084320	168.327190	169.970497	170.250009	169.586669	169.193808	168.647059	154.230304	157.384666	159.875833	162.873029	165.294373	167.283045	169.199672	171.779093	172.741832	171.561610	170.901329	169.233327	166.393007	164.213914	161.106829	158.347805	156.387507	154.533309	153.534547	155.421271	157.151047	161.582298	165.105482	168.556656	170.161282	171.258714	171.712329	170.605609	155.830705	158.925806	161.461264	164.444072	166.928101	168.903843	171.323183	173.520670	174.071135	172.390639	170.145948	167.581461	163.885631	160.611328	158.018576	155.311127	153.376434	151.855436	151.620943	153.796685	154.422400	158.468111	163.212275	166.433036	169.593043	172.281515	173.850300	172.896012	157.402003	160.520379	163.058314	166.141213	168.598871	170.722819	173.018794	174.443817	174.020215	171.751703	168.351994	164.296121	161.050810	156.629612	153.326279	151.576216	150.739137	149.966563	150.438062	153.271135	152.942743	155.216682	161.491204	165.650774	168.639628	172.264615	174.539756	174.682134	158.846075	161.752541	164.530249	167.580514	169.948206	172.433764	174.474522	175.143653	173.405682	169.977163	165.883300	161.072919	157.550974	152.822437	148.594573	148.244691	148.499071	147.988199	148.529120	151.403861	151.833946	153.425642	160.038317	165.317101	168.145147	172.207795	175.376325	175.928574	160.099982	162.971444	165.856347	168.996248	171.511892	174.004735	175.432672	175.278164	172.270260	167.938518	162.532107	156.678856	152.990603	148.095502	144.542051	144.688581	145.06090	145.205791	146.869350	148.760117	150.335239	153.650592	160.017483	164.604662	168.745911	172.683701	176.080423	176.930687	161.397414	164.299253	167.207977	170.362411	173.080605	175.428665	176.834201	175.620834	171.970424	165.470479	158.158186	151.607212	147.331269	142.878893	139.502167	140.188527	141.137352	142.994646	145.776871	148.646877	149.941140	153.755928	159.616026	163.935895	169.204699	173.785977	177.046294	178.104498	162.579931	165.378656	168.472810	171.594646	174.663522	176.927299	178.096449	175.952249	171.158878	163.103369	153.904134	146.029430	141.161828	136.577090	133.400073	135.594791	138.899435	142.058168	145.066545	149.497250	151.243671	154.257585	159.644509	163.419851	168.667711	174.550974	178.079293	179.142342	163.781788	166.678674	169.987033	173.169222	176.006920	178.192351	178.726862	176.490038	170.169477	160.270151	149.649463	140.813149	136.216828	131.726061	127.942160	131.710545	137.707958	141.114223	144.424331	148.334985	151.056565	154.796685	159.096740	162.625423	167.858386	174.990530	178.557458	179.312439	164.919140	167.928793	171.471608	174.825970	177.054562	179.503187	179.291022	176.500929	170.187762	158.495429	145.924713	136.634238	131.573229	127.617993	125.622765	130.467856	137.432417	140.690876	143.755382	146.837407	149.371044	153.29175	157.372282	160.996321	166.32373	174.621344	178.387980	179.411801	165.862976	168.936915	172.494555	175.736551	178.434675	180.798543	179.938627	176.329157	169.455072	157.910872	144.057148	133.780696	127.059734	125.350647	126.683446	130.524750	136.524058	140.367620	143.143289	144.546822	145.975924	150.059552	155.012639	159.095975	165.904935	174.664979	178.689710	179.810526	166.774759	169.953633	173.398834	176.629721	179.658095	181.766891	181.321981	177.549882	169.748206	157.851794	143.743216	132.160517	125.364888	124.901985	128.924349	133.287015	137.574904	140.161683	141.822109	142.285449	143.300710	146.955309	152.252122	158.019924	166.267893	174.022874	178.723366	180.08523	167.560554	170.725077	174.122018	177.309051	180.472009	182.719432	182.218394	178.913276	170.979129	158.472701	143.462247	132.679439	126.813586	126.825387	131.366090	135.609506	139.074668	141.059333	140.945766	141.111528	141.182517	144.245602	150.105081	157.269823	166.691204	173.993808	178.192460	179.213732	167.993262	171.204116	174.603387	177.97811	180.971845	182.992533	182.511637	179.383937	171.634675	159.379712	145.166964	134.738809	129.977199	130.437042	133.006374	137.059297	140.584557	141.560408	139.732180	139.207977	138.706356	141.691386	148.981679	158.296813	168.453979	174.154544	177.583792	178.938736	167.592788	171.162994	174.589073	177.954908	180.775997	182.331451	182.398470	179.366272	172.345766	160.552686	148.194354	137.927773	133.710727	134.238864	136.713641	138.885704	141.611801	141.184593	138.126352	136.040102	136.096012	141.095975	150.249900	161.824185	170.249499	175.461519	178.353451	178.846221	166.415043	170.231725	173.948534	177.244400	179.818977	181.153597	181.888946	179.719250	172.965544	162.529776	151.198980	141.735130	137.952103	138.750137	140.775779	142.422837	142.979894	140.340776	136.618321	133.168858	135.165726	142.817374	154.137571	165.153597	172.243489	177.444655	178.950756	178.269823	164.713313	168.328647	172.190457	175.241741	177.782080	179.361537	180.014751	178.739064	172.904134	163.943908	154.005828	145.599417	141.973593	141.274558	143.146786	144.671426	142.871827	138.371335	133.792388	132.228009	137.290366	147.177308	159.438572	168.499690	174.297068	177.513131	177.871754	176.596977	162.829139	166.214533	169.220980	172.075724	174.945984	176.700273	177.484320	176.777454	171.878638	163.918084	155.588854	148.586633	144.153815	142.741067	144.292296	144.697286	141.352832	135.527481	132.314223	134.889201	141.741978	151.980951	162.910909	169.837370	174.045201	175.976252	175.761027	174.493753	161.250410	164.043307	166.194136	168.697359	171.239374	173.050592	174.268075	173.820652	169.845748	163.176070	155.916044	149.891932	144.926935	142.940484	143.330177	142.309415	138.403606	134.085959	134.029466	138.084793	146.508468	156.861373	165.039701	170.151958	173.581461	174.240794	173.489710	172.680568	159.230195	161.710253	163.483701	165.520779	167.203023	169.009033	170.133273	169.651175	166.728829	161.822983	155.839191	149.785722	144.802622	142.034129	141.457585	139.342415	135.820543	134.204844	135.291131	140.705190	150.273539	159.804043	166.696194	170.803096	172.547405	172.215516	171.403642	170.865635	155.466764	157.719177	159.16802	161.077581	162.395083	163.957312	164.415407	163.768239	161.939938	158.738445	154.004771	147.938518	143.131634	139.984192	138.519323	136.431069	134.377563	134.012129	136.160153	142.979712	153.355564	161.015917	166.234456	169.803132	170.497359	169.920306	169.202295	168.562921	151.226334	152.917137	154.173812	156.229576	157.714442	159.216026	159.278638	158.280495	157.055655	155.039920	150.594500	145.369368	140.655946	137.464761	135.660244	133.949117	133.231943	133.220215	137.090912	145.385139	155.083992	160.937643	165.098197	167.691750	168.030195	167.698197	166.982153	166.277509	147.123803	148.348607	149.754617	151.619304	153.333710	154.011765	153.487598	152.768858	151.640248	149.348534	146.573484	142.390384	138.580222	136.411036	134.006119	131.549044	131.949918	134.583755	139.361974	148.115862	155.095465	160.346858	163.915607	165.364414	165.911273	165.182080	164.407977	163.488254	143.407758	144.189474	145.711637	147.660718	149.019414	148.670843	148.185212	147.298926	146.286323	144.027062	142.966017	139.769550	137.071572	135.277181	131.922783	130.232235	132.046367	135.289237	141.104863	147.495611	153.325806	159.125332	161.969259	162.736696	162.906137	161.966454	161.137898	159.824731
std	7.287552	41.358555	39.942152	39.056286	38.595247	37.111165	36.125579	35.016392	33.661998	32.651607	31.279244	30.558445	29.771007	29.329251	28.620248	27.961255	27.053544	26.763535	26.307419	26.088459	26.475963	26.940885	27.871515	29.368386	30.906718	31.902723	34.303747	35.991306	36.571064	41.555429	40.094304	39.427215	38.686176	37.242459	36.373576	35.242915	33.899171	32.759395	31.656140	30.833853	30.285472	30.014701	29.488345	28.877079	28.385090	28.071306	27.385837	27.169745	27.054699	27.287977	28.346384	29.614235	31.048117	32.299271	34.411090	35.837702	36.584178	41.778308	40.241183	39.766083	38.811304	37.558850	36.738919	35.524369	34.143523	33.366659	32.706590	31.540195	30.919631	31.734199	31.376934	31.711126	32.105972	31.567277	30.990092	30.646945	29.567699	29.121604	29.950303	30.060839	31.848742	33.397800	34.833426	36.160581	37.130147	42.029500	40.510134	39.982096	38.990179	37.831990	37.013307	35.994198	34.803070	34.186032	33.590485	33.023394	32.332933	33.489875	34.131590	35.504633	36.163043	36.267805	36.035518	35.554383	33.995554	32.618142	32.169005	31.606215	33.091450	33.799247	35.040408	36.543966	37.008573	42.230596	40.722846	40.269497	39.286656	38.055911	37.175998	36.414078	35.364973	35.137786	34.791087	35.670272	35.450400	37.389018	38.142135	39.028650	40.237810	40.801754	41.360760	40.621785	38.440031	37.704805	35.661038	34.722326	34.627536	34.460804	35.585550	35.856267	36.379407	42.520489	41.141604	40.665904	39.471974	38.243671	37.468092	36.637765	36.111578	35.828897	36.202284	37.995085	39.124282	40.007543	41.764678	43.127948	43.690112	44.329521	44.391484	44.608277	42.813879	42.149745	39.864605	38.087663	36.059258	35.490495	35.179224	34.845038	35.917254	42.686980	41.425780	41.015447	39.706068	38.707245	37.621740	36.678723	36.607763	36.198828	37.750438	40.092848	41.412790	42.751692	44.994999	46.082327	46.480810	47.257773	46.664866	46.438683	44.591409	44.680532	42.393541	40.104588	38.489088	36.673132	34.925551	33.608328	34.730713	42.783174	41.585817	41.339247	39.894171	39.207617	38.036799	37.430985	37.344942	37.873361	39.445123	42.723254	44.317912	44.981873	47.585207	47.755564	48.124048	48.186147	46.947563	46.768885	45.488701	46.041979	45.495555	42.661805	40.823591	39.054250	36.386452	34.316857	33.832094	42.986343	41.969817	41.541042	40.412780	39.693188	38.378560	37.851723	38.009317	38.899522	41.045157	44.584033	46.041528	46.827974	49.090368	49.440601	48.585840	47.982886	47.585353	47.303372	45.387759	46.301803	46.965949	44.785083	42.550474	41.179438	37.335756	34.736565	33.794241	43.334310	42.460100	42.004419	40.955459	40.292639	38.197912	38.107000	38.597378	39.889654	42.921361	45.329351	46.935892	48.345221	49.573104	49.508355	48.611495	47.86773	47.759402	47.854134	47.118160	47.278849	48.001876	45.920356	43.625525	40.753489	38.167379	34.732093	34.434877	43.667002	42.883307	42.140379	41.090449	40.344930	38.540337	38.624698	39.290984	41.271550	44.798345	47.068909	48.107023	48.774274	49.837125	49.600538	48.367929	48.565419	48.543205	48.931035	48.194725	47.963615	48.720651	46.713019	45.092546	41.522295	38.880070	34.767673	34.245483	43.917995	43.255520	42.113002	41.174804	40.166780	38.944201	39.261357	40.121785	42.336360	45.966951	48.836116	49.928701	50.157866	51.181726	50.046819	48.902870	50.326335	50.267419	49.867515	48.503102	48.419363	48.906813	46.980377	46.057195	43.246102	39.527382	36.103995	34.546056	43.933083	43.136405	41.918544	41.026460	40.054835	39.351904	40.369145	41.172182	43.104622	47.071433	49.937849	50.648017	50.730912	51.422481	51.252661	49.846747	50.943771	51.323190	50.301512	49.146169	49.413640	48.697965	47.608506	47.590411	44.747602	39.831635	37.198715	35.792995	44.104308	43.411408	42.053777	41.172844	40.447399	40.126154	41.186312	41.730232	44.068295	47.941677	50.020959	50.989468	50.643443	51.144372	50.956894	51.106043	51.800618	51.472043	50.558362	50.179273	50.397042	49.67878	48.670011	49.210489	46.51766	41.778188	38.464118	37.841808	44.367527	43.773834	42.318724	41.635380	41.088562	40.571813	41.006124	42.624014	45.482039	48.306048	49.573526	49.748005	50.133302	50.234619	50.402747	51.829862	52.612133	52.246332	51.675397	51.558525	50.962162	51.483887	50.773570	50.991611	47.702531	43.271017	39.812806	38.628440	44.734481	44.075152	42.669953	42.365795	41.600537	41.016695	41.313907	43.158295	46.164683	47.751418	49.166332	49.594843	49.568748	50.732567	51.652906	53.629683	53.745496	53.890071	52.968585	51.923949	51.924891	53.238049	52.730098	52.457900	49.444810	44.966384	42.013979	40.44858	45.122056	44.306051	43.161115	43.096720	41.986319	40.998546	41.529168	43.223175	45.952033	47.577955	48.153488	48.497473	49.906946	51.492235	53.677052	54.936786	54.970760	55.541516	53.431099	52.101316	52.537648	53.588788	54.351671	53.491590	50.757713	47.083811	44.029288	42.583125	45.326658	44.633778	43.679628	43.60682	42.246818	41.032229	42.145044	43.617781	46.053796	47.823937	48.127729	48.857155	50.477645	53.437553	54.795758	56.111923	55.939864	55.202311	53.209616	51.239624	52.316325	53.598076	55.917288	54.188452	51.553497	48.303020	45.779313	44.672685	45.870159	45.082930	44.360838	44.150074	42.795383	42.149035	42.765427	44.633559	46.203566	48.606101	48.720199	49.034127	50.544436	53.504578	55.221908	56.935795	55.720427	54.249338	51.360469	50.905418	52.647791	54.931210	57.197665	55.032350	52.927331	49.306868	47.452352	46.392674	46.918532	45.989082	45.178991	44.715976	43.869189	43.122641	43.117747	44.834245	46.514149	48.493541	49.104975	48.656682	50.991415	52.701899	54.613006	55.513007	55.232457	52.678025	50.329868	50.896196	53.022342	56.653193	58.076049	56.522666	53.579719	49.816612	48.095602	47.808138	47.792090	47.110084	46.368032	45.535543	44.540787	43.644227	43.698046	44.923752	46.431540	47.999209	48.757032	48.673817	51.269215	52.091283	53.910823	54.318384	53.650325	51.710436	50.754592	51.569382	54.977137	58.445599	57.787255	56.791071	53.546746	50.889420	50.040698	50.334770	48.663201	48.316535	47.898254	47.072906	46.117702	45.408085	44.837023	45.749846	47.272157	48.650843	49.054784	49.201845	50.264820	51.128225	52.156931	53.078386	52.925047	51.972113	50.556698	53.450780	57.449880	59.106513	58.592734	56.539071	54.082713	52.595619	52.119543	52.660055	49.796694	49.350564	49.771640	49.272314	48.600859	47.715438	47.166406	47.469815	48.921759	49.419971	49.601527	49.164146	49.704754	49.929268	51.045191	52.393291	52.352515	51.888322	52.700578	56.292015	58.698748	59.895568	58.865256	57.201302	55.484131	54.840932	54.494393	54.538267	50.457155	50.507701	51.209278	50.398698	50.713131	50.258163	49.240510	49.429988	50.066609	50.291321	50.107081	49.593373	49.635372	49.565189	50.493717	51.953341	52.262539	53.060074	55.216992	58.386391	60.544561	60.368488	59.313495	57.399857	56.667567	56.966751	56.824345	56.402894	51.850388	51.782992	52.52728	52.416922	52.901234	52.313785	52.091616	51.416181	51.800803	51.709716	51.478392	50.572205	49.928662	49.093708	50.528777	52.251552	53.375389	55.731283	57.696790	60.709611	61.767661	61.271725	59.730246	58.566942	58.248748	58.624993	58.745069	58.482183	53.092065	53.306515	53.920602	53.548103	53.525993	53.310340	53.612331	53.632965	54.082230	53.256292	53.078511	51.819515	50.874587	49.963778	51.206310	53.437942	55.607151	58.007756	60.902711	62.301631	62.526226	61.889131	60.529388	60.523591	60.360628	60.566993	60.968961	60.688955	54.035002	53.633619	54.747464	54.306448	54.008754	54.752529	54.371094	55.134335	56.230943	55.466736	54.602459	53.765855	52.422790	52.008350	53.572756	55.869388	57.586028	60.373218	63.301768	63.300608	63.511566	62.551522	61.833119	62.210750	62.163516	61.958245	61.950177	62.403709	54.406116	53.658786	54.710497	54.613724	54.351761	55.233710	55.904715	57.155523	57.965677	57.393379	56.689603	56.118823	54.680900	55.278778	56.384076	58.111783	59.204300	62.553694	63.751194	65.512894	64.427412	63.708507	63.738316	63.444008	63.509210	63.298721	63.610415	64.396846
min	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	17.000000	23.000000	28.000000	34.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	18.000000	25.000000	30.000000	36.000000	9.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	19.000000	10.000000	18.000000	32.000000	24.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	5.000000	8.000000	16.000000	14.000000	8.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	1.000000	0.000000	4.000000	8.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	8.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	9.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	12.000000	3.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	6.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	2.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.00000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	1.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.00000	0.000000	0.000000	0.00000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	4.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.00000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	6.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.00000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	3.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.00000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	6.000000	121.000000	126.000000	130.000000	133.000000	137.000000	140.000000	142.000000	144.000000	146.000000	148.000000	150.000000	151.000000	152.000000	153.000000	153.000000	154.000000	154.000000	154.000000	155.000000	154.000000	154.000000	154.000000	153.000000	152.000000	151.000000	149.000000	147.000000	147.000000	123.000000	128.000000	132.000000	135.000000	139.000000	141.000000	144.000000	146.000000	148.000000	149.000000	151.000000	152.000000	152.000000	153.000000	154.000000	154.000000	154.000000	155.000000	154.000000	155.000000	155.000000	155.000000	154.000000	154.000000	152.000000	150.000000	149.000000	148.000000	125.000000	130.000000	134.000000	137.000000	140.000000	143.000000	146.000000	148.000000	150.000000	150.000000	152.000000	153.000000	153.000000	153.000000	151.000000	150.000000	151.000000	151.000000	152.000000	153.000000	154.000000	155.000000	155.000000	155.000000	154.000000	152.000000	151.000000	150.000000	127.000000	132.000000	136.000000	139.000000	142.000000	145.000000	148.000000	150.000000	151.000000	151.000000	152.000000	154.000000	151.000000	151.000000	147.000000	145.000000	144.000000	143.000000	143.000000	147.000000	150.000000	153.000000	155.000000	155.000000	155.000000	154.000000	153.000000	152.000000	129.000000	133.000000	138.000000	141.000000	144.000000	147.000000	149.000000	152.000000	152.000000	152.000000	151.000000	151.000000	148.000000	146.000000	142.000000	138.000000	136.000000	132.000000	132.000000	137.000000	141.000000	147.000000	151.000000	154.000000	155.000000	155.000000	155.000000	154.000000	130.000000	135.000000	139.000000	142.000000	146.000000	148.000000	151.000000	153.000000	154.000000	151.000000	150.000000	148.000000	144.000000	140.000000	135.000000	131.000000	128.000000	125.000000	123.000000	128.000000	130.000000	139.000000	146.000000	152.000000	154.000000	156.000000	157.000000	156.000000	132.000000	137.000000	140.000000	144.000000	147.000000	150.000000	153.000000	154.000000	155.000000	152.000000	148.000000	145.000000	139.000000	133.000000	129.000000	124.000000	122.000000	119.000000	119.000000	124.000000	124.000000	132.000000	142.000000	147.000000	152.000000	156.000000	159.000000	158.000000	134.000000	138.000000	142.000000	146.000000	149.000000	151.000000	154.000000	155.000000	154.000000	151.000000	145.000000	138.000000	134.000000	126.000000	122.000000	119.000000	117.000000	116.000000	117.000000	123.000000	121.000000	125.000000	138.000000	145.000000	151.000000	156.000000	159.000000	159.000000	135.000000	140.000000	143.000000	147.000000	150.000000	153.000000	155.000000	155.000000	152.000000	147.000000	140.000000	133.000000	128.000000	119.000000	114.000000	114.000000	115.000000	113.000000	114.000000	120.000000	119.000000	121.000000	133.000000	144.000000	150.000000	155.000000	160.000000	160.000000	136.000000	141.000000	145.000000	149.000000	152.000000	154.000000	155.000000	154.000000	150.000000	143.000000	135.000000	126.000000	121.000000	113.000000	108.000000	110.000000	111.00000	110.000000	111.000000	114.000000	116.000000	119.000000	131.000000	141.000000	149.000000	155.000000	160.000000	161.000000	138.000000	142.000000	146.000000	150.000000	153.000000	155.000000	156.000000	154.000000	148.000000	138.000000	127.000000	118.000000	113.000000	107.000000	103.000000	106.000000	106.000000	107.000000	109.000000	113.000000	115.000000	119.000000	129.000000	139.000000	149.000000	157.000000	161.000000	162.000000	139.000000	143.000000	147.000000	151.000000	155.000000	156.000000	156.000000	153.000000	146.000000	134.000000	120.000000	109.000000	104.000000	98.000000	96.000000	100.000000	103.000000	104.000000	107.000000	114.000000	116.000000	118.000000	128.500000	136.000000	148.000000	157.000000	162.000000	163.000000	140.000000	145.000000	149.000000	153.000000	156.000000	158.000000	156.000000	153.000000	144.000000	129.000000	114.000000	103.000000	98.000000	93.000000	89.000000	96.000000	101.000000	103.000000	106.000000	112.000000	114.000000	119.000000	126.000000	133.000000	146.000000	157.500000	163.000000	164.000000	141.000000	146.000000	150.000000	154.000000	156.000000	158.000000	157.000000	152.000000	143.000000	125.000000	109.000000	97.000000	93.000000	90.000000	88.000000	93.000000	100.000000	102.000000	106.000000	109.000000	111.000000	116.00000	122.000000	128.000000	143.00000	157.000000	162.000000	164.000000	142.000000	147.000000	151.000000	155.000000	157.000000	159.000000	157.000000	151.000000	140.000000	124.000000	108.000000	97.000000	89.000000	88.000000	90.000000	93.000000	98.000000	101.000000	104.000000	105.000000	107.000000	110.000000	116.000000	122.000000	141.000000	157.000000	163.000000	165.000000	143.000000	148.000000	152.000000	156.000000	158.000000	160.000000	158.000000	152.000000	139.000000	125.000000	108.000000	95.000000	88.500000	87.000000	90.000000	93.000000	98.000000	99.000000	101.000000	103.000000	103.000000	105.000000	110.000000	118.000000	141.000000	156.000000	164.000000	166.00000	144.000000	148.000000	152.000000	156.000000	159.000000	160.000000	158.000000	153.000000	141.000000	125.000000	109.000000	97.000000	90.000000	88.000000	91.000000	94.000000	97.000000	98.000000	101.000000	102.000000	101.000000	102.000000	106.000000	117.000000	139.000000	157.000000	164.000000	165.000000	144.000000	149.000000	153.000000	157.00000	159.000000	161.000000	159.000000	154.000000	142.000000	127.000000	111.000000	99.000000	93.000000	90.000000	91.000000	94.000000	98.000000	99.000000	100.000000	101.000000	99.000000	100.000000	103.000000	117.000000	143.000000	157.000000	163.000000	166.000000	143.000000	148.000000	152.000000	156.000000	159.000000	161.000000	159.000000	154.000000	143.000000	127.000000	114.000000	102.500000	96.000000	94.000000	93.000000	94.000000	100.000000	100.000000	100.000000	98.000000	96.000000	97.000000	102.000000	123.000000	148.000000	160.000000	165.000000	166.000000	140.000000	145.000000	150.000000	155.000000	158.000000	159.000000	159.000000	154.000000	143.000000	129.000000	117.000000	107.000000	100.000000	99.000000	98.000000	100.000000	101.000000	101.000000	100.000000	96.000000	95.000000	97.000000	105.000000	130.000000	154.000000	164.000000	166.000000	166.000000	136.000000	142.000000	147.000000	151.000000	155.000000	156.000000	156.000000	152.000000	143.000000	131.000000	120.000000	110.000000	103.000000	102.000000	103.000000	104.000000	103.000000	100.000000	96.000000	94.000000	95.000000	98.000000	114.000000	142.000000	159.000000	164.000000	165.000000	164.000000	133.000000	138.000000	143.000000	146.000000	150.000000	152.000000	152.000000	149.000000	142.000000	131.000000	121.000000	113.000000	107.000000	105.000000	106.000000	106.000000	102.000000	97.000000	95.000000	95.000000	96.000000	102.000000	120.000000	147.000000	159.000000	162.000000	162.000000	161.000000	129.000000	133.000000	135.000000	139.000000	141.000000	145.000000	146.000000	145.000000	140.000000	130.000000	122.000000	115.000000	109.000000	107.000000	107.000000	104.000000	100.000000	96.000000	95.000000	94.000000	98.000000	107.000000	125.000000	149.000000	158.000000	160.000000	159.000000	159.000000	125.000000	129.000000	129.000000	132.000000	135.000000	138.000000	139.000000	139.000000	135.000000	129.000000	121.000000	115.000000	110.000000	108.000000	106.000000	102.000000	98.000000	96.000000	94.000000	95.000000	100.000000	112.000000	133.000000	151.000000	156.000000	157.000000	156.000000	156.000000	118.000000	120.000000	121.00000	123.000000	125.000000	128.000000	129.000000	128.000000	127.000000	124.000000	119.000000	113.000000	109.000000	107.000000	103.000000	99.000000	96.000000	93.000000	92.000000	94.000000	103.000000	114.000000	132.000000	149.000000	152.000000	152.000000	152.000000	152.000000	111.000000	112.000000	113.000000	115.000000	117.000000	119.000000	119.000000	120.000000	119.000000	119.000000	115.000000	110.000000	106.000000	104.000000	100.000000	96.000000	93.000000	90.000000	90.000000	96.000000	104.000000	116.000000	130.000000	140.000000	144.000000	145.000000	146.000000	147.000000	107.000000	108.000000	109.000000	110.000000	112.000000	113.000000	112.000000	113.000000	111.000000	111.000000	109.000000	106.000000	104.000000	102.000000	97.000000	92.000000	91.000000	90.000000	90.000000	98.000000	104.000000	115.000000	127.000000	132.000000	137.000000	138.000000	140.000000	138.000000	104.000000	104.000000	105.000000	106.000000	107.000000	107.000000	106.000000	106.000000	105.000000	104.000000	104.000000	102.000000	102.000000	99.000000	94.000000	90.000000	90.000000	89.000000	92.000000	96.000000	103.000000	112.000000	120.000000	125.000000	128.000000	128.000000	128.000000	125.500000
50%	13.000000	150.000000	153.000000	156.000000	158.000000	160.000000	162.000000	164.000000	165.000000	166.000000	167.000000	168.000000	169.000000	170.000000	170.000000	171.000000	171.000000	171.000000	171.000000	171.000000	170.000000	170.000000	170.000000	169.000000	168.000000	168.000000	167.000000	166.000000	165.000000	152.000000	155.000000	157.000000	160.000000	162.000000	164.000000	166.000000	167.000000	168.000000	169.000000	170.000000	171.000000	171.000000	172.000000	172.000000	171.000000	171.000000	172.000000	171.000000	171.000000	171.000000	171.000000	171.000000	170.000000	169.000000	168.000000	167.000000	167.000000	154.000000	157.000000	159.000000	162.000000	164.000000	166.000000	168.000000	169.000000	170.000000	171.000000	172.000000	172.000000	172.000000	172.000000	171.000000	171.000000	171.000000	171.000000	171.000000	171.000000	172.000000	172.000000	172.000000	171.000000	171.000000	170.000000	169.000000	168.000000	156.000000	159.000000	162.000000	164.000000	166.000000	168.000000	170.000000	171.000000	172.000000	172.000000	173.000000	173.000000	173.000000	172.000000	171.000000	169.000000	168.000000	168.000000	168.000000	169.000000	170.000000	172.000000	172.000000	172.000000	172.000000	171.000000	171.000000	170.000000	158.000000	161.000000	164.000000	166.000000	168.000000	170.000000	171.000000	173.000000	174.000000	174.000000	174.000000	174.000000	172.000000	171.000000	169.000000	167.000000	166.000000	164.000000	164.000000	165.000000	168.000000	170.000000	172.000000	173.000000	173.000000	173.000000	172.000000	172.000000	160.000000	163.000000	165.000000	168.000000	170.000000	171.000000	173.000000	175.000000	176.000000	175.000000	175.000000	174.000000	171.000000	169.000000	167.000000	164.000000	163.000000	161.000000	160.000000	162.000000	164.000000	168.000000	171.000000	173.000000	174.000000	174.000000	174.000000	174.000000	162.000000	165.000000	167.000000	170.000000	172.000000	173.000000	175.000000	177.000000	178.000000	176.000000	175.000000	173.000000	170.000000	167.000000	165.000000	161.000000	160.000000	157.000000	158.000000	160.000000	162.000000	166.000000	170.000000	172.000000	174.000000	175.000000	176.000000	175.000000	163.000000	166.000000	169.000000	172.000000	174.000000	175.000000	177.000000	179.000000	178.000000	177.000000	175.000000	171.000000	167.000000	163.000000	159.000000	157.000000	156.000000	154.000000	156.000000	159.000000	160.000000	164.000000	169.000000	173.000000	174.000000	176.000000	177.000000	177.000000	165.000000	168.000000	170.000000	173.000000	175.000000	177.000000	179.000000	180.000000	178.000000	175.000000	172.000000	167.000000	163.000000	159.000000	153.000000	152.000000	152.000000	151.000000	152.000000	156.000000	158.000000	162.000000	169.000000	173.000000	175.000000	177.000000	178.000000	178.000000	166.000000	169.000000	172.000000	175.000000	177.000000	179.000000	180.000000	179.000000	177.000000	174.000000	168.000000	162.000000	157.000000	152.000000	148.000000	147.000000	147.00000	147.000000	151.000000	153.000000	156.000000	162.000000	169.000000	173.000000	176.000000	178.000000	179.000000	179.000000	168.000000	171.000000	174.000000	176.000000	179.000000	180.000000	181.000000	180.000000	177.000000	171.000000	163.000000	155.000000	151.000000	144.000000	140.000000	142.000000	142.000000	144.000000	149.000000	152.000000	155.000000	162.000000	169.000000	174.000000	177.000000	179.000000	180.000000	181.000000	169.000000	172.000000	175.000000	178.000000	180.000000	181.000000	182.000000	180.000000	176.000000	169.000000	158.000000	148.000000	143.000000	137.000000	133.000000	136.000000	139.000000	144.000000	147.000000	153.000000	156.000000	162.000000	169.000000	173.000000	177.000000	180.000000	182.000000	182.000000	171.000000	174.000000	177.000000	179.000000	182.000000	183.000000	183.000000	182.000000	175.000000	166.000000	153.000000	141.000000	137.000000	131.000000	126.000000	131.000000	138.000000	142.000000	146.000000	151.000000	156.000000	162.000000	168.000000	173.000000	177.000000	181.000000	183.000000	182.000000	172.000000	175.000000	178.000000	181.000000	182.000000	184.000000	184.000000	182.000000	175.000000	163.000000	148.000000	136.000000	131.000000	127.000000	124.000000	130.000000	138.000000	142.000000	146.000000	150.000000	154.000000	160.00000	166.000000	173.000000	177.00000	182.000000	183.000000	183.000000	173.000000	176.000000	179.000000	182.000000	184.000000	186.000000	185.000000	182.000000	175.000000	162.000000	145.000000	132.000000	125.000000	124.000000	125.000000	129.000000	137.000000	142.000000	145.000000	146.000000	149.000000	156.000000	164.000000	171.000000	177.000000	183.000000	184.000000	184.000000	174.000000	177.000000	180.000000	183.000000	185.000000	187.000000	187.000000	183.000000	175.000000	161.000000	144.000000	130.000000	123.000000	122.000000	127.000000	132.000000	137.000000	141.000000	144.000000	145.000000	144.000000	151.000000	161.000000	171.000000	179.000000	183.000000	185.000000	185.00000	175.000000	178.000000	181.000000	184.000000	186.000000	188.000000	187.000000	185.000000	176.000000	162.000000	144.000000	131.000000	125.000000	125.000000	128.000000	135.000000	138.000000	143.000000	143.000000	142.000000	142.000000	146.000000	158.000000	170.000000	180.000000	185.000000	186.000000	186.000000	176.000000	179.000000	182.000000	185.00000	187.000000	188.000000	188.000000	185.000000	177.000000	162.000000	146.000000	134.000000	128.000000	128.000000	129.000000	136.000000	141.000000	144.000000	141.000000	139.000000	139.000000	141.000000	157.000000	172.000000	182.000000	185.000000	186.000000	187.000000	175.000000	179.000000	182.000000	185.000000	187.000000	188.000000	189.000000	186.000000	177.000000	164.000000	149.000000	137.000000	133.000000	132.000000	134.000000	138.000000	141.000000	141.000000	138.000000	135.000000	133.000000	140.000000	161.000000	178.000000	185.000000	187.000000	188.000000	187.000000	174.000000	178.000000	182.000000	185.000000	187.000000	188.000000	188.000000	186.000000	178.000000	166.000000	153.000000	142.000000	138.000000	137.000000	140.000000	143.000000	143.000000	139.000000	135.000000	130.000000	130.000000	143.000000	168.000000	182.000000	186.000000	189.000000	189.000000	188.000000	173.000000	176.000000	180.000000	183.000000	186.000000	186.000000	187.000000	185.000000	178.000000	168.000000	157.000000	147.000000	143.000000	141.000000	143.000000	145.000000	142.000000	137.000000	133.000000	128.000000	132.000000	154.000000	176.000000	186.000000	188.000000	189.000000	189.000000	188.000000	171.000000	174.000000	178.000000	180.000000	183.000000	185.000000	184.000000	184.000000	178.000000	168.000000	159.000000	151.000000	145.000000	143.000000	146.000000	145.000000	140.000000	133.000000	129.000000	129.000000	141.000000	164.000000	181.000000	187.000000	188.000000	189.000000	188.000000	187.000000	169.000000	172.000000	175.000000	178.000000	181.000000	182.000000	183.000000	181.000000	177.000000	169.000000	161.000000	153.000000	146.000000	144.000000	145.000000	142.000000	137.000000	131.000000	130.000000	134.000000	152.000000	173.000000	184.000000	187.000000	189.000000	189.000000	188.000000	187.000000	166.000000	170.000000	173.000000	175.000000	177.000000	179.000000	179.000000	178.000000	174.000000	168.000000	161.000000	153.000000	147.000000	143.000000	142.000000	139.000000	134.000000	131.000000	130.000000	138.000000	162.000000	178.000000	186.000000	188.000000	189.000000	188.000000	188.000000	187.000000	162.000000	165.000000	168.00000	170.000000	172.000000	174.000000	174.000000	172.000000	170.000000	166.000000	160.000000	152.000000	145.000000	141.000000	138.000000	135.000000	132.000000	129.000000	131.000000	146.000000	169.000000	181.000000	186.000000	187.000000	188.000000	187.000000	187.000000	186.000000	157.000000	159.000000	161.000000	164.000000	166.000000	167.000000	168.000000	167.000000	165.000000	163.000000	157.000000	150.000000	143.000000	138.000000	135.000000	132.000000	129.000000	127.000000	134.000000	153.000000	173.000000	181.000000	184.000000	187.000000	187.000000	187.000000	186.000000	185.000000	151.000000	152.000000	155.000000	157.000000	160.000000	161.000000	161.000000	159.000000	159.000000	157.000000	153.000000	147.000000	141.000000	138.000000	133.000000	129.000000	127.000000	130.000000	139.000000	161.000000	175.000000	181.000000	184.000000	185.000000	186.000000	185.000000	184.000000	184.000000	145.000000	146.000000	149.000000	151.000000	153.000000	153.000000	154.000000	152.000000	153.000000	152.000000	150.000000	146.000000	141.000000	137.000000	131.000000	128.000000	128.000000	132.000000	144.000000	162.000000	172.000000	180.000000	183.000000	184.000000	184.000000	182.000000	182.000000	182.000000
75%	19.000000	174.000000	176.000000	178.000000	179.000000	181.000000	182.000000	183.000000	184.000000	185.000000	186.000000	186.000000	187.000000	187.000000	187.000000	188.000000	188.000000	188.000000	187.000000	187.000000	187.000000	187.000000	186.000000	186.000000	186.000000	185.000000	184.000000	184.000000	183.000000	176.000000	178.000000	180.000000	181.000000	183.000000	184.000000	185.000000	186.000000	187.000000	187.000000	188.000000	188.000000	188.000000	189.000000	189.000000	189.000000	189.000000	189.000000	188.000000	188.000000	188.000000	188.000000	188.000000	187.000000	187.000000	186.000000	185.000000	185.000000	178.000000	180.000000	182.000000	183.000000	185.000000	186.000000	187.000000	188.000000	189.000000	189.000000	190.000000	190.000000	190.000000	190.000000	190.000000	189.000000	189.000000	189.000000	189.000000	189.000000	189.000000	189.000000	189.000000	189.000000	188.000000	188.000000	187.000000	187.000000	180.000000	182.000000	184.000000	185.000000	187.000000	188.000000	189.000000	190.000000	191.000000	191.000000	192.000000	192.000000	192.000000	192.000000	191.000000	189.000000	189.000000	188.000000	188.000000	188.000000	189.000000	190.000000	190.000000	190.000000	190.000000	189.000000	189.000000	189.000000	182.000000	184.000000	186.000000	187.000000	188.000000	190.000000	191.000000	192.000000	193.000000	193.000000	193.000000	193.000000	193.000000	192.000000	190.000000	189.000000	188.000000	187.000000	186.000000	187.000000	188.000000	189.000000	190.000000	191.000000	191.000000	191.000000	191.000000	190.500000	184.000000	186.000000	187.000000	189.000000	190.000000	191.000000	193.000000	195.000000	195.000000	195.000000	195.000000	195.000000	193.000000	193.000000	191.000000	189.000000	188.000000	186.000000	186.000000	186.000000	187.000000	189.000000	190.000000	191.000000	192.000000	193.000000	193.000000	192.000000	186.000000	188.000000	189.000000	191.000000	192.000000	193.000000	195.000000	197.000000	197.000000	196.000000	196.000000	195.000000	193.000000	192.000000	191.000000	188.000000	187.000000	186.000000	186.000000	186.000000	186.000000	188.000000	190.000000	192.000000	193.000000	194.000000	194.000000	194.000000	188.000000	189.000000	191.000000	193.000000	194.000000	195.000000	197.000000	198.000000	198.000000	197.000000	196.000000	194.000000	192.000000	190.000000	188.000000	187.000000	186.000000	184.000000	185.000000	186.000000	186.000000	188.000000	191.000000	193.000000	194.000000	195.000000	195.000000	195.000000	189.000000	191.000000	193.000000	195.000000	196.000000	197.000000	199.000000	199.000000	199.000000	197.000000	196.000000	193.000000	190.000000	188.000000	185.000000	184.000000	184.000000	183.000000	184.000000	184.000000	186.000000	188.000000	191.000000	194.000000	195.000000	196.000000	197.000000	197.000000	191.000000	193.000000	194.000000	196.000000	198.000000	199.000000	200.000000	200.000000	199.000000	197.000000	194.000000	190.000000	187.000000	184.000000	182.000000	180.000000	180.00000	181.000000	183.000000	184.000000	186.000000	189.000000	193.000000	194.000000	195.000000	197.000000	198.000000	198.000000	192.000000	194.000000	196.000000	198.000000	200.000000	201.000000	202.000000	201.000000	199.000000	196.000000	192.000000	187.000000	183.000000	180.000000	177.000000	176.000000	177.000000	180.000000	183.000000	185.000000	186.000000	189.000000	193.000000	195.000000	197.000000	198.000000	199.000000	199.500000	194.000000	195.000000	197.000000	199.000000	201.000000	202.000000	204.000000	202.000000	200.000000	195.000000	190.000000	184.000000	179.000000	174.000000	171.000000	171.000000	176.000000	181.000000	184.000000	186.000000	188.000000	191.000000	193.000000	195.000000	197.000000	200.000000	201.000000	201.000000	195.000000	197.000000	199.000000	201.000000	202.000000	204.000000	205.000000	204.000000	200.000000	194.000000	187.000000	179.000000	174.000000	170.000000	166.000000	168.000000	176.000000	181.000000	184.000000	186.000000	189.000000	191.000000	194.000000	196.000000	198.000000	200.000000	202.000000	201.000000	196.000000	198.000000	200.000000	202.000000	204.000000	205.000000	206.000000	205.000000	201.000000	194.000000	184.000000	175.000000	169.000000	164.000000	162.000000	168.000000	176.000000	181.000000	183.000000	186.000000	188.000000	191.00000	194.000000	196.000000	198.00000	201.000000	202.000000	202.000000	198.000000	200.000000	201.000000	203.000000	206.000000	207.000000	207.000000	206.000000	202.000000	194.000000	181.000000	171.000000	163.000000	160.000000	163.000000	168.000000	176.000000	181.000000	183.000000	185.000000	186.000000	190.000000	194.000000	196.000000	199.000000	202.000000	203.000000	203.000000	199.000000	201.000000	202.000000	204.000000	207.000000	209.000000	209.000000	208.000000	203.000000	193.000000	180.000000	168.000000	160.000000	161.000000	166.000000	174.000000	178.000000	182.000000	183.000000	183.000000	185.000000	190.000000	193.000000	197.000000	200.000000	203.000000	204.000000	204.00000	200.000000	201.000000	204.000000	206.000000	208.000000	210.000000	210.000000	209.000000	204.000000	193.000000	178.000000	167.000000	162.000000	163.000000	170.000000	177.000000	181.000000	185.000000	182.000000	182.000000	183.000000	188.000000	194.000000	198.000000	202.000000	204.000000	205.000000	205.000000	200.000000	202.000000	205.000000	207.00000	209.000000	210.000000	211.000000	210.000000	205.000000	194.000000	179.000000	169.000000	166.000000	169.000000	174.500000	181.000000	184.000000	184.000000	181.000000	178.000000	180.000000	186.000000	195.000000	199.000000	203.000000	205.000000	206.000000	206.000000	200.000000	202.000000	205.000000	208.000000	209.000000	210.000000	212.000000	210.000000	205.000000	196.000000	183.000000	173.000000	170.000000	174.000000	179.500000	184.000000	184.000000	183.000000	176.000000	174.000000	178.000000	187.000000	196.000000	202.000000	206.000000	206.000000	207.000000	207.000000	200.000000	202.000000	205.000000	208.000000	209.000000	210.000000	212.000000	211.000000	206.000000	198.000000	187.000000	177.000000	174.000000	178.000000	183.000000	186.000000	185.000000	181.000000	174.000000	170.000000	178.000000	191.000000	200.000000	205.000000	207.000000	208.000000	208.000000	207.000000	199.000000	202.000000	205.000000	207.000000	208.000000	209.000000	210.000000	211.000000	206.000000	199.000000	189.000000	180.000000	179.000000	180.000000	184.000000	186.000000	184.000000	177.000000	171.000000	170.000000	184.000000	196.000000	203.000000	207.000000	208.000000	208.000000	208.000000	207.000000	199.000000	201.000000	204.000000	205.000000	207.000000	208.000000	209.000000	210.000000	206.000000	200.000000	192.000000	184.000000	180.500000	180.000000	183.000000	185.000000	182.000000	175.000000	168.000000	178.000000	191.000000	200.000000	206.000000	208.000000	208.000000	208.000000	207.000000	207.000000	198.000000	201.000000	203.000000	204.000000	206.000000	207.000000	208.000000	209.000000	205.000000	199.000000	192.000000	185.000000	181.000000	179.000000	180.000000	181.000000	178.000000	173.000000	174.000000	186.000000	196.000000	203.000000	207.000000	208.000000	209.000000	208.000000	207.000000	206.000000	197.000000	199.000000	201.000000	202.000000	204.000000	205.000000	206.000000	206.000000	203.000000	199.000000	192.000000	185.500000	180.000000	177.000000	177.000000	177.000000	174.000000	174.000000	181.000000	191.000000	201.000000	206.000000	208.000000	208.000000	208.000000	208.000000	207.000000	206.000000	195.000000	197.000000	199.00000	200.000000	202.000000	203.000000	203.000000	202.000000	201.000000	197.000000	192.000000	184.000000	179.000000	174.000000	174.000000	175.000000	174.000000	178.000000	185.000000	195.000000	203.000000	206.000000	208.000000	208.000000	208.000000	208.000000	207.000000	206.000000	193.000000	194.000000	196.000000	197.000000	199.000000	200.000000	199.000000	199.000000	198.000000	195.000000	189.000000	182.000000	177.000000	172.000000	171.000000	172.000000	176.000000	181.000000	190.000000	199.000000	204.000000	206.000000	208.000000	208.000000	208.000000	208.000000	207.000000	206.000000	190.000000	191.000000	193.000000	195.000000	196.000000	196.000000	195.000000	196.000000	195.000000	191.000000	187.000000	181.000000	176.000000	173.000000	172.000000	172.000000	177.000000	186.000000	195.000000	201.000000	205.000000	207.000000	207.000000	208.000000	208.000000	207.000000	206.000000	205.000000	187.000000	187.000000	190.000000	192.000000	193.000000	193.000000	192.000000	193.000000	192.000000	188.000000	185.000000	181.000000	176.000000	174.000000	172.000000	173.000000	180.000000	189.000000	196.000000	202.000000	205.000000	207.000000	208.000000	207.000000	207.000000	206.000000	204.000000	204.000000
max	24.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.00000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.00000	255.000000	255.000000	255.00000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.00000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.00000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.00000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000	255.000000

# Surface the features that have NaNs
null_counts = Xy_original.isnull().sum()
if null_counts.sum() > 0 :
    print(null_counts[null_counts > 0])
print('Total number of NaN in the dataframe:', null_counts.sum())

Total number of NaN in the dataframe: 0

1.d) Data Cleaning

# Standardize the class column to the name of targetVar if required
Xy_original = Xy_original.rename(columns={'label': 'targetVar'})

1.e) Splitting Data into Sets

# Use variable totCol to hold the number of columns in the dataframe
totCol = len(Xy_original.columns)

# Set up variable totAttr for the total number of attribute columns
totAttr = totCol-1

# targetCol variable indicates the column location of the target/class variable
# If the first column, set targetCol to 1. If the last column, set targetCol to totCol
# If (targetCol <> 1) and (targetCol <> totCol), be aware when slicing up the dataframes for visualization
targetCol = 1

# We create attribute-only and target-only datasets (X_original and y_original)
# for various visualization and cleaning/transformation operations

if targetCol == totCol:
    X_train_df = Xy_original.iloc[:,0:totAttr]
    y_train_df = Xy_original.iloc[:,totAttr]
else:
    X_train_df = Xy_original.iloc[:,1:totCol]
    y_train_df = Xy_original.iloc[:,0]

print("Xy_original.shape: {} X_train_df.shape: {} y_train_df.shape: {}".format(Xy_original.shape, X_train_df.shape, y_train_df.shape))

Xy_original.shape: (27455, 785) X_train_df.shape: (27455, 784) y_train_df.shape: (27455,)

dataset_path = 'https://dainesanalytics.com/datasets/kaggle-sign-language-mnist/sign_mnist_test.csv'
Xy_test = pd.read_csv(dataset_path, sep=',')

# Take a peek at the dataframe after import
Xy_test.head()

	label	pixel1	pixel2	pixel3	pixel4	pixel5	pixel6	pixel7	pixel8	pixel9	pixel10	pixel11	pixel12	pixel13	pixel14	pixel15	pixel16	pixel17	pixel18	pixel19	pixel20	pixel21	pixel22	pixel23	pixel24	pixel25	pixel26	pixel27	pixel28	pixel29	pixel30	pixel31	pixel32	pixel33	pixel34	pixel35	pixel36	pixel37	pixel38	pixel39	pixel40	pixel41	pixel42	pixel43	pixel44	pixel45	pixel46	pixel47	pixel48	pixel49	pixel50	pixel51	pixel52	pixel53	pixel54	pixel55	pixel56	pixel57	pixel58	pixel59	pixel60	pixel61	pixel62	pixel63	pixel64	pixel65	pixel66	pixel67	pixel68	pixel69	pixel70	pixel71	pixel72	pixel73	pixel74	pixel75	pixel76	pixel77	pixel78	pixel79	pixel80	pixel81	pixel82	pixel83	pixel84	pixel85	pixel86	pixel87	pixel88	pixel89	pixel90	pixel91	pixel92	pixel93	pixel94	pixel95	pixel96	pixel97	pixel98	pixel99	pixel100	pixel101	pixel102	pixel103	pixel104	pixel105	pixel106	pixel107	pixel108	pixel109	pixel110	pixel111	pixel112	pixel113	pixel114	pixel115	pixel116	pixel117	pixel118	pixel119	pixel120	pixel121	pixel122	pixel123	pixel124	pixel125	pixel126	pixel127	pixel128	pixel129	pixel130	pixel131	pixel132	pixel133	pixel134	pixel135	pixel136	pixel137	pixel138	pixel139	pixel140	pixel141	pixel142	pixel143	pixel144	pixel145	pixel146	pixel147	pixel148	pixel149	pixel150	pixel151	pixel152	pixel153	pixel154	pixel155	pixel156	pixel157	pixel158	pixel159	pixel160	pixel161	pixel162	pixel163	pixel164	pixel165	pixel166	pixel167	pixel168	pixel169	pixel170	pixel171	pixel172	pixel173	pixel174	pixel175	pixel176	pixel177	pixel178	pixel179	pixel180	pixel181	pixel182	pixel183	pixel184	pixel185	pixel186	pixel187	pixel188	pixel189	pixel190	pixel191	pixel192	pixel193	pixel194	pixel195	pixel196	pixel197	pixel198	pixel199	pixel200	pixel201	pixel202	pixel203	pixel204	pixel205	pixel206	pixel207	pixel208	pixel209	pixel210	pixel211	pixel212	pixel213	pixel214	pixel215	pixel216	pixel217	pixel218	pixel219	pixel220	pixel221	pixel222	pixel223	pixel224	pixel225	pixel226	pixel227	pixel228	pixel229	pixel230	pixel231	pixel232	pixel233	pixel234	pixel235	pixel236	pixel237	pixel238	pixel239	pixel240	pixel241	pixel242	pixel243	pixel244	pixel245	pixel246	pixel247	pixel248	pixel249	pixel250	pixel251	pixel252	pixel253	pixel254	pixel255	pixel256	pixel257	pixel258	pixel259	pixel260	pixel261	pixel262	pixel263	pixel264	pixel265	pixel266	pixel267	pixel268	pixel269	pixel270	pixel271	pixel272	pixel273	pixel274	pixel275	pixel276	pixel277	pixel278	pixel279	pixel280	pixel281	pixel282	pixel283	pixel284	pixel285	pixel286	pixel287	pixel288	pixel289	pixel290	pixel291	pixel292	pixel293	pixel294	pixel295	pixel296	pixel297	pixel298	pixel299	pixel300	pixel301	pixel302	pixel303	pixel304	pixel305	pixel306	pixel307	pixel308	pixel309	pixel310	pixel311	pixel312	pixel313	pixel314	pixel315	pixel316	pixel317	pixel318	pixel319	pixel320	pixel321	pixel322	pixel323	pixel324	pixel325	pixel326	pixel327	pixel328	pixel329	pixel330	pixel331	pixel332	pixel333	pixel334	pixel335	pixel336	pixel337	pixel338	pixel339	pixel340	pixel341	pixel342	pixel343	pixel344	pixel345	pixel346	pixel347	pixel348	pixel349	pixel350	pixel351	pixel352	pixel353	pixel354	pixel355	pixel356	pixel357	pixel358	pixel359	pixel360	pixel361	pixel362	pixel363	pixel364	pixel365	pixel366	pixel367	pixel368	pixel369	pixel370	pixel371	pixel372	pixel373	pixel374	pixel375	pixel376	pixel377	pixel378	pixel379	pixel380	pixel381	pixel382	pixel383	pixel384	pixel385	pixel386	pixel387	pixel388	pixel389	pixel390	pixel391	pixel392	pixel393	pixel394	pixel395	pixel396	pixel397	pixel398	pixel399	pixel400	pixel401	pixel402	pixel403	pixel404	pixel405	pixel406	pixel407	pixel408	pixel409	pixel410	pixel411	pixel412	pixel413	pixel414	pixel415	pixel416	pixel417	pixel418	pixel419	pixel420	pixel421	pixel422	pixel423	pixel424	pixel425	pixel426	pixel427	pixel428	pixel429	pixel430	pixel431	pixel432	pixel433	pixel434	pixel435	pixel436	pixel437	pixel438	pixel439	pixel440	pixel441	pixel442	pixel443	pixel444	pixel445	pixel446	pixel447	pixel448	pixel449	pixel450	pixel451	pixel452	pixel453	pixel454	pixel455	pixel456	pixel457	pixel458	pixel459	pixel460	pixel461	pixel462	pixel463	pixel464	pixel465	pixel466	pixel467	pixel468	pixel469	pixel470	pixel471	pixel472	pixel473	pixel474	pixel475	pixel476	pixel477	pixel478	pixel479	pixel480	pixel481	pixel482	pixel483	pixel484	pixel485	pixel486	pixel487	pixel488	pixel489	pixel490	pixel491	pixel492	pixel493	pixel494	pixel495	pixel496	pixel497	pixel498	pixel499	pixel500	pixel501	pixel502	pixel503	pixel504	pixel505	pixel506	pixel507	pixel508	pixel509	pixel510	pixel511	pixel512	pixel513	pixel514	pixel515	pixel516	pixel517	pixel518	pixel519	pixel520	pixel521	pixel522	pixel523	pixel524	pixel525	pixel526	pixel527	pixel528	pixel529	pixel530	pixel531	pixel532	pixel533	pixel534	pixel535	pixel536	pixel537	pixel538	pixel539	pixel540	pixel541	pixel542	pixel543	pixel544	pixel545	pixel546	pixel547	pixel548	pixel549	pixel550	pixel551	pixel552	pixel553	pixel554	pixel555	pixel556	pixel557	pixel558	pixel559	pixel560	pixel561	pixel562	pixel563	pixel564	pixel565	pixel566	pixel567	pixel568	pixel569	pixel570	pixel571	pixel572	pixel573	pixel574	pixel575	pixel576	pixel577	pixel578	pixel579	pixel580	pixel581	pixel582	pixel583	pixel584	pixel585	pixel586	pixel587	pixel588	pixel589	pixel590	pixel591	pixel592	pixel593	pixel594	pixel595	pixel596	pixel597	pixel598	pixel599	pixel600	pixel601	pixel602	pixel603	pixel604	pixel605	pixel606	pixel607	pixel608	pixel609	pixel610	pixel611	pixel612	pixel613	pixel614	pixel615	pixel616	pixel617	pixel618	pixel619	pixel620	pixel621	pixel622	pixel623	pixel624	pixel625	pixel626	pixel627	pixel628	pixel629	pixel630	pixel631	pixel632	pixel633	pixel634	pixel635	pixel636	pixel637	pixel638	pixel639	pixel640	pixel641	pixel642	pixel643	pixel644	pixel645	pixel646	pixel647	pixel648	pixel649	pixel650	pixel651	pixel652	pixel653	pixel654	pixel655	pixel656	pixel657	pixel658	pixel659	pixel660	pixel661	pixel662	pixel663	pixel664	pixel665	pixel666	pixel667	pixel668	pixel669	pixel670	pixel671	pixel672	pixel673	pixel674	pixel675	pixel676	pixel677	pixel678	pixel679	pixel680	pixel681	pixel682	pixel683	pixel684	pixel685	pixel686	pixel687	pixel688	pixel689	pixel690	pixel691	pixel692	pixel693	pixel694	pixel695	pixel696	pixel697	pixel698	pixel699	pixel700	pixel701	pixel702	pixel703	pixel704	pixel705	pixel706	pixel707	pixel708	pixel709	pixel710	pixel711	pixel712	pixel713	pixel714	pixel715	pixel716	pixel717	pixel718	pixel719	pixel720	pixel721	pixel722	pixel723	pixel724	pixel725	pixel726	pixel727	pixel728	pixel729	pixel730	pixel731	pixel732	pixel733	pixel734	pixel735	pixel736	pixel737	pixel738	pixel739	pixel740	pixel741	pixel742	pixel743	pixel744	pixel745	pixel746	pixel747	pixel748	pixel749	pixel750	pixel751	pixel752	pixel753	pixel754	pixel755	pixel756	pixel757	pixel758	pixel759	pixel760	pixel761	pixel762	pixel763	pixel764	pixel765	pixel766	pixel767	pixel768	pixel769	pixel770	pixel771	pixel772	pixel773	pixel774	pixel775	pixel776	pixel777	pixel778	pixel779	pixel780	pixel781	pixel782	pixel783	pixel784
0	6	149	149	150	150	150	151	151	150	151	152	152	152	152	152	153	153	151	152	152	153	152	152	151	151	150	150	150	149	150	150	150	152	152	151	152	152	152	152	152	153	154	153	154	154	153	154	153	154	153	153	152	152	152	151	150	151	150	151	151	152	152	152	153	153	152	152	152	153	154	154	155	155	154	154	155	155	155	155	154	153	153	151	151	152	150	151	151	152	152	152	154	154	154	154	154	153	154	155	156	157	157	156	155	156	155	154	154	155	152	154	153	153	151	152	152	152	154	154	154	154	154	155	157	156	156	156	154	150	146	147	146	147	143	137	126	126	142	139	152	154	152	153	153	154	154	155	154	155	155	154	153	150	144	143	145	139	142	144	157	157	147	139	128	119	130	113	147	156	151	153	153	155	155	156	155	152	145	139	141	141	141	153	153	143	135	137	139	133	121	107	101	104	110	127	157	156	151	152	153	155	155	154	151	146	139	131	130	134	137	132	125	111	101	94	95	105	113	122	133	145	153	157	156	156	152	152	154	152	151	150	149	149	139	122	104	98	92	82	81	81	85	114	145	157	160	162	161	159	157	156	156	156	151	151	150	146	145	147	148	147	145	132	97	71	62	66	88	116	145	162	160	159	157	155	156	157	157	156	155	155	151	145	144	145	147	145	147	150	150	124	92	68	63	67	86	159	163	155	158	157	156	156	157	156	156	156	155	154	143	144	145	145	143	147	152	152	128	90	79	68	64	70	67	84	147	164	157	158	157	157	157	156	157	156	156	155	145	146	143	145	145	150	149	149	139	118	85	62	62	75	73	62	67	140	164	157	158	158	158	158	157	157	156	156	150	147	144	147	149	148	149	158	158	136	94	63	58	69	85	82	67	70	156	160	159	160	159	158	157	156	156	156	147	148	147	145	148	152	151	160	153	119	86	66	64	63	69	75	78	57	130	165	158	159	158	159	158	157	157	157	149	148	146	145	147	149	146	151	144	110	78	65	66	66	58	59	64	79	150	165	162	162	162	162	161	161	158	156	151	146	143	141	138	140	142	146	144	121	84	56	62	70	71	68	57	117	144	144	147	149	152	150	146	146	154	160	147	144	143	142	140	142	146	151	154	131	85	59	51	60	85	69	64	76	75	79	81	79	76	83	112	141	163	163	144	148	147	145	145	148	150	155	151	119	74	62	63	55	62	72	73	77	74	73	68	88	113	138	162	162	168	168	146	146	142	141	141	138	134	142	124	96	75	67	65	63	62	78	87	76	84	96	126	162	172	155	144	149	151	161	142	136	132	134	127	119	118	119	103	87	77	73	70	62	64	72	93	134	155	160	166	156	150	151	143	136	145	149	130	132	127	120	114	110	109	105	91	77	74	75	74	65	73	113	166	177	170	161	152	141	134	136	140	133	127	130	113	116	115	106	101	95	86	84	85	77	78	74	76	103	152	179	170	157	155	151	140	129	126	126	133	130	122	125	81	86	85	83	76	72	73	76	77	79	71	101	151	178	177	170	161	152	147	151	133	115	121	121	124	126	122	122	61	61	67	69	70	75	78	78	81	68	113	165	174	169	162	157	149	148	148	148	126	100	113	117	113	122	118	115	69	69	77	78	75	76	78	79	67	120	173	157	159	148	155	150	138	143	148	149	123	91	101	111	111	116	113	118	74	75	76	75	75	76	75	68	124	172	152	146	146	146	152	142	131	134	144	147	125	87	87	103	107	110	116	113	75	74	74	74	76	74	82	134	168	155	146	137	145	146	149	135	124	125	138	148	127	89	82	96	106	112	120	107
1	5	126	128	131	132	133	134	135	135	136	138	137	137	138	138	139	137	142	140	138	139	137	137	136	135	134	133	134	132	129	132	134	135	135	137	139	139	139	140	141	141	142	143	142	142	116	138	141	140	141	140	139	138	137	136	136	134	133	135	138	139	139	141	142	143	142	143	145	145	143	145	145	158	94	118	151	143	144	144	142	141	141	140	139	138	137	139	142	142	142	144	146	146	146	147	147	147	148	117	128	168	101	98	157	146	147	146	146	145	144	143	142	141	140	142	145	146	147	148	149	149	149	151	151	149	161	114	99	174	99	84	162	149	151	149	148	147	146	146	145	144	143	145	149	150	150	151	153	153	154	153	154	152	167	126	88	169	99	87	164	152	153	152	151	150	149	148	148	147	145	147	151	152	153	155	155	155	151	154	158	155	170	130	79	166	111	93	166	156	157	156	155	153	152	152	152	150	149	150	153	155	155	158	157	163	129	120	166	156	171	140	82	162	102	97	168	158	160	158	162	160	154	154	154	152	151	152	156	158	159	159	158	164	139	91	165	159	174	144	71	156	96	100	171	161	161	158	128	145	162	156	155	155	152	155	159	160	161	161	160	168	158	76	159	164	172	142	63	155	117	100	174	159	164	164	126	103	162	161	158	157	153	157	160	162	162	162	164	167	158	78	158	167	167	156	73	133	129	102	172	157	148	130	156	132	129	163	161	159	157	159	162	164	164	165	166	167	173	89	139	172	162	163	79	98	132	111	170	160	142	54	125	150	102	150	167	162	159	161	166	165	167	167	167	168	178	118	112	175	164	167	82	91	129	110	160	156	130	96	157	130	106	169	165	164	159	162	166	167	168	168	170	169	164	168	132	141	162	153	103	113	117	96	133	143	107	147	172	99	139	174	165	166	161	164	167	170	171	171	170	173	160	173	162	129	132	132	109	109	108	99	135	142	111	163	154	77	156	172	167	167	165	167	168	171	172	173	173	174	169	170	182	150	125	124	100	106	103	102	130	138	124	178	130	64	168	172	170	169	165	168	170	171	172	174	175	174	175	172	195	170	114	110	94	89	98	105	127	134	124	182	126	80	180	171	171	171	166	169	171	172	173	174	175	176	177	174	197	179	119	86	87	81	94	118	136	123	116	177	127	94	183	172	173	173	169	172	172	174	175	174	177	178	178	175	192	176	126	87	86	82	109	130	147	159	128	164	128	100	184	174	173	173	169	172	173	173	176	178	179	178	181	175	189	171	126	89	80	90	121	137	164	175	141	140	108	95	184	176	175	173	171	173	174	175	177	179	179	179	181	174	189	171	134	91	80	98	134	159	164	167	153	114	73	82	185	176	177	177	172	173	174	177	178	179	180	180	183	174	186	172	138	93	82	97	143	172	169	160	132	89	44	108	189	176	178	178	171	173	177	178	179	180	181	182	185	178	179	170	137	95	88	90	152	180	167	141	112	65	64	176	183	179	179	178	173	174	178	179	179	180	182	183	186	175	165	168	137	100	96	88	149	168	147	122	92	50	144	193	181	181	180	179	173	174	177	179	180	180	183	182	187	177	158	161	130	111	101	91	136	150	135	112	62	87	192	183	185	183	181	180	173	174	177	178	179	179	181	182	184	179	156	151	124	116	96	88	128	138	126	81	49	164	190	184	185	184	182	181	172	174	177	178	178	178	180	182	184	177	160	154	128	114	97	78	114	112	89	48	133	194	182	185	184	184	182	181	172	174	177	178	178	179	181	183	187	175	165	154	118	107	100	75	96	83	47	104	194	183	186	184	184	184	182	180
2	10	85	88	92	96	105	123	135	143	147	152	157	163	168	171	182	172	175	185	183	184	185	185	185	183	183	182	181	178	86	88	93	96	108	125	137	145	149	154	160	166	170	174	215	154	142	190	184	184	186	187	185	184	183	183	181	179	86	89	93	98	110	127	138	147	150	155	162	169	171	183	214	162	123	187	188	187	189	188	187	186	185	185	183	181	88	91	95	99	111	128	141	149	152	157	165	171	175	184	215	182	116	179	193	190	191	190	189	186	187	186	186	183	88	92	96	99	113	130	144	151	154	160	167	173	180	181	215	206	128	169	198	192	192	192	191	191	191	188	187	186	89	93	98	101	116	133	145	152	155	162	169	175	181	182	226	217	138	157	203	193	194	195	193	193	193	191	189	187	91	94	99	102	118	135	147	154	157	164	172	179	185	183	225	213	148	146	205	196	197	198	196	196	195	193	191	190	91	95	100	101	118	136	149	156	159	167	174	180	186	184	228	223	148	128	205	199	200	200	199	197	196	196	193	193	91	94	99	102	120	139	152	157	161	167	176	184	187	186	232	232	161	112	201	202	201	201	200	199	199	198	195	195	92	95	100	104	123	138	152	163	165	177	209	150	170	194	223	211	162	101	187	208	203	203	203	202	201	200	198	198	92	97	101	106	120	159	193	150	116	161	193	103	127	204	214	191	148	91	168	214	205	206	205	203	203	203	201	200	93	97	101	108	119	176	191	111	86	99	141	104	66	164	205	167	157	95	160	218	206	207	207	205	204	204	202	202	93	98	100	108	126	150	151	113	100	90	128	113	71	72	128	133	166	118	136	220	207	208	208	208	206	205	205	203	94	98	101	109	128	145	159	161	154	142	144	119	101	70	72	93	130	124	105	209	211	210	210	209	208	208	207	205	95	98	101	109	129	147	162	169	181	186	132	138	120	111	85	75	100	108	85	190	220	213	212	210	210	210	208	206	95	98	102	110	129	148	164	167	198	181	101	120	165	146	125	94	83	93	75	179	224	215	215	214	213	211	209	207	93	97	102	112	132	149	166	173	189	195	158	91	127	176	152	132	101	80	69	156	228	215	216	216	214	212	210	208	95	99	100	110	135	147	186	190	153	207	171	108	110	222	169	152	128	79	61	108	226	217	218	218	216	215	213	212	96	99	101	111	134	146	200	221	149	156	161	113	167	247	188	160	139	90	63	92	223	221	220	219	219	217	216	214	95	99	101	112	135	150	187	222	172	113	168	151	173	247	184	153	140	103	67	90	226	223	222	222	220	218	217	216	96	98	101	113	136	155	168	194	184	123	170	201	176	229	196	157	133	107	74	88	225	224	224	224	222	220	218	217	95	98	101	115	137	155	167	183	185	125	169	250	154	197	201	172	130	102	81	86	224	226	225	224	224	222	220	218	94	97	100	115	137	156	171	173	198	163	190	173	100	162	200	161	125	98	80	95	228	227	226	225	224	223	221	219	96	99	100	114	138	157	173	174	190	225	194	116	125	184	183	150	117	94	77	112	236	226	229	227	225	224	221	220	93	97	99	115	138	157	170	175	177	211	222	197	172	191	163	135	110	97	76	132	239	224	227	227	225	224	223	222	91	94	97	114	137	156	170	172	180	199	217	200	157	160	147	122	112	107	80	145	239	225	227	227	225	224	222	221	90	92	96	114	138	155	171	174	185	90	179	207	143	164	167	163	145	123	78	162	239	227	229	226	226	225	224	222	89	91	94	111	136	154	167	184	125	3	166	225	195	188	172	185	161	122	68	166	242	227	230	227	226	225	224	222
3	0	203	205	207	206	207	209	210	209	210	209	208	207	207	209	208	210	210	207	209	209	208	209	210	209	207	208	209	207	206	208	209	208	208	210	211	210	211	209	209	210	211	211	209	208	211	215	210	212	212	211	211	210	210	211	210	210	209	209	210	211	210	210	212	212	211	212	210	210	212	211	223	208	162	176	219	204	206	217	216	214	212	209	211	212	209	210	211	213	215	213	211	213	213	211	216	216	179	167	228	202	161	129	132	155	141	187	210	159	197	217	211	211	210	211	211	213	214	213	213	214	215	216	245	228	181	138	184	210	175	160	76	133	143	118	180	126	170	225	211	214	210	212	213	213	213	215	213	221	198	181	245	225	192	156	176	234	181	168	95	158	159	121	145	134	161	228	214	216	211	213	214	215	215	215	218	252	199	142	192	244	200	166	160	249	199	175	102	176	164	113	111	137	131	232	213	217	213	214	214	215	217	211	235	246	207	174	164	250	211	166	144	248	204	171	96	179	161	98	94	152	85	209	221	217	214	216	216	216	214	233	229	227	222	190	140	226	220	160	123	239	206	155	77	138	144	88	82	161	76	141	233	216	215	216	217	216	217	237	194	217	235	197	131	193	228	158	100	198	194	137	69	105	127	78	84	166	89	111	231	218	217	217	219	214	230	230	180	192	229	195	129	156	217	151	87	153	177	128	78	88	114	64	102	178	106	115	233	220	217	218	218	216	230	223	188	176	204	173	118	121	191	141	81	110	168	123	74	88	117	74	157	195	120	119	234	222	213	216	215	221	232	209	174	140	183	167	113	96	178	139	71	82	166	122	64	111	127	97	196	189	122	128	235	221	213	215	215	215	246	229	187	129	145	170	101	83	169	144	70	75	173	120	130	197	163	118	184	196	122	138	234	220	215	217	216	217	244	231	192	146	100	141	131	79	171	165	82	85	170	173	196	194	173	137	132	180	112	145	236	221	217	218	217	221	248	235	206	169	123	109	140	103	164	178	148	189	206	203	191	177	154	137	114	117	91	138	238	220	218	219	219	221	249	243	214	182	164	151	142	164	185	198	218	220	218	207	189	170	143	121	113	92	73	131	239	220	217	218	217	222	244	243	223	200	185	173	160	160	187	205	218	217	218	209	183	164	142	114	99	93	66	159	238	222	216	216	217	221	238	238	231	215	204	182	170	165	178	201	215	216	211	202	177	157	136	110	96	76	113	222	230	227	222	223	224	216	233	239	240	229	210	187	171	168	180	207	218	218	203	194	174	153	129	107	80	97	213	227	225	226	175	180	188	178	214	240	245	233	210	191	174	167	179	211	220	211	196	186	168	143	118	96	78	196	239	230	234	233	94	96	103	85	151	244	234	226	211	195	181	165	178	207	207	192	178	168	153	129	107	86	104	177	178	182	178	177	103	103	104	91	114	239	220	212	211	202	188	164	173	203	198	178	156	140	127	115	95	92	99	95	90	86	113	156	101	103	105	99	106	230	209	204	214	204	185	164	167	201	194	168	131	109	103	93	93	104	98	97	131	187	234	233	100	101	100	102	104	222	207	205	215	199	183	172	164	193	187	153	107	91	86	93	102	108	141	195	241	242	226	207	100	101	100	104	98	222	224	209	212	193	178	175	159	171	173	135	92	85	85	92	120	208	252	255	246	237	229	204	101	100	100	102	93	220	233	219	210	191	179	182	155	159	164	123	85	80	84	151	238	255	255	250	237	245	250	232	103	101	102	103	95	208	231	227	209	190	179	182	152	150	159	119	83	63	154	248	247	248	253	236	230	240	253	255
4	3	188	191	193	195	199	201	202	203	203	203	204	204	204	203	202	198	216	217	135	181	200	195	194	193	190	189	187	185	190	194	196	197	200	202	204	206	207	207	206	205	206	206	205	200	220	206	122	155	207	196	195	195	193	191	188	187	192	195	198	199	203	205	206	208	209	209	209	208	208	207	207	202	219	195	123	146	209	197	197	197	195	191	190	188	193	197	200	201	204	207	209	210	211	211	211	210	210	209	208	205	219	197	123	142	209	199	200	197	195	194	192	190	196	199	202	204	206	209	211	212	213	213	213	212	212	212	210	206	223	221	143	135	207	202	201	200	197	196	194	191	199	201	203	207	209	211	213	215	216	216	216	216	215	213	212	207	229	225	143	127	206	203	202	201	198	196	195	193	199	203	206	209	212	214	216	217	218	218	218	217	216	216	215	208	234	215	133	125	209	205	203	202	200	197	196	195	201	205	209	211	215	217	219	220	221	220	220	220	218	218	217	210	234	214	136	127	212	208	206	204	202	199	197	196	203	207	211	215	217	218	221	222	223	223	223	223	222	220	219	215	245	211	138	127	212	209	208	206	204	201	200	197	205	209	213	216	218	221	223	225	225	226	225	225	224	221	222	211	196	171	117	125	218	209	209	208	205	202	199	197	206	211	215	218	221	224	226	227	228	228	228	227	225	228	248	205	135	103	83	146	224	210	211	210	206	204	201	199	208	213	217	220	224	226	227	229	230	230	229	226	224	206	203	208	162	122	67	188	226	212	214	212	209	206	203	201	210	214	218	222	225	227	230	230	232	232	226	241	241	173	112	174	233	151	109	168	210	221	216	213	210	208	205	203	210	216	219	223	226	229	231	233	228	236	199	159	215	180	130	150	240	144	123	104	137	161	215	215	211	210	208	205	211	217	221	224	228	231	232	232	247	248	200	135	166	204	149	127	202	154	142	123	154	116	187	223	211	211	209	207	213	218	222	226	229	232	232	240	251	234	220	177	135	198	148	114	166	166	154	134	149	103	177	226	213	213	210	208	212	218	223	226	230	233	232	255	250	221	229	182	128	167	147	113	156	127	118	148	127	93	174	229	214	215	212	210	212	217	223	226	230	232	232	249	242	194	200	180	120	134	144	96	185	187	100	170	156	95	150	230	214	213	211	209	215	219	224	229	231	234	236	238	238	212	199	159	99	128	128	77	180	194	104	152	162	92	130	230	215	214	210	207	215	220	225	228	231	234	236	242	251	233	211	148	123	132	141	105	164	168	143	145	133	87	174	227	213	214	215	218	214	220	226	229	231	234	235	240	255	240	226	153	131	131	155	168	220	197	168	147	97	115	229	227	228	225	204	161	217	223	229	233	235	238	241	243	255	249	221	169	150	139	203	232	209	176	139	131	93	182	234	193	166	138	92	66	165	165	167	169	170	170	167	167	238	245	212	191	163	154	214	223	188	155	131	118	95	124	103	65	50	47	54	59	139	141	140	141	140	137	140	124	201	244	213	195	177	145	180	191	162	136	120	100	70	49	47	50	57	54	47	50	147	148	147	147	147	148	158	126	124	242	215	194	176	136	137	135	129	115	100	70	53	56	57	49	48	58	53	46	148	148	146	146	146	146	148	121	64	148	207	197	154	117	119	116	119	91	54	69	46	43	53	52	44	48	56	55	148	150	151	149	148	149	143	95	79	74	115	144	125	120	112	105	93	52	24	53	63	33	41	51	48	45	49	55	149	150	150	148	147	151	124	82	84	81	69	81	111	103	84	75	53	28	26	40	64	48	29	46	49	46	46	53

# Standardize the class column to the name of targetVar if required
Xy_test = Xy_test.rename(columns={'label': 'targetVar'})

X_test_df = Xy_test.iloc[:,1:totCol]
y_test_df = Xy_test.iloc[:,0]
print("Xy_test.shape: {} X_test_df.shape: {} y_test_df.shape: {}".format(Xy_test.shape, X_test_df.shape, y_test_df.shape))

Xy_test.shape: (7172, 785) X_test_df.shape: (7172, 784) y_test_df.shape: (7172,)

if notifyStatus: status_notify('(TensorFlow Multi-Class) Task 1 - Prepare Environment completed on ' + datetime.now().strftime('%A %B %d, %Y %I:%M:%S %p'))

Task 2 - Summarize and Visualize Data

if notifyStatus: status_notify('(TensorFlow Multi-Class) Task 2 - Summarize and Visualize Data has begun on ' + datetime.now().strftime('%A %B %d, %Y %I:%M:%S %p'))

# Set up the number of row and columns for visualization display. dispRow * dispCol should be >= totAttr
dispCol = 4
if totAttr % dispCol == 0 :
    dispRow = totAttr // dispCol
else :
    dispRow = (totAttr // dispCol) + 1
    
# Set figure width to display the data visualization plots
fig_size = plt.rcParams["figure.figsize"]
fig_size[0] = dispCol*4
fig_size[1] = dispRow*4
plt.rcParams["figure.figsize"] = fig_size

# Histograms for each attribute
X_train_df.hist(layout=(dispRow,dispCol))
plt.show()

# Box and Whisker plot for each attribute
X_train_df.plot(kind='box', subplots=True, layout=(dispRow,dispCol))
plt.show()

# Correlation matrix
fig = plt.figure(figsize=(16,12))
ax = fig.add_subplot(111)
correlations = X_train_df.corr(method='pearson')
cax = ax.matshow(correlations, vmin=-1, vmax=1)
fig.colorbar(cax)
plt.show()

if notifyStatus: status_notify('(TensorFlow Multi-Class) Task 2 - Summarize and Visualize Data completed on ' + datetime.now().strftime('%A %B %d, %Y %I:%M:%S %p'))

Task 3 - Pre-process Data

if notifyStatus: status_notify('(TensorFlow Multi-Class) Task 3 - Pre-process Data has begun on ' + datetime.now().strftime('%A %B %d, %Y %I:%M:%S %p'))

3.a) Feature Scaling

# Compose pipeline for the numerical and categorical features
numeric_columns = X_train_df.select_dtypes(include=['int','float']).columns
numeric_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='constant', fill_value=0)),
    ('scaler', preprocessing.StandardScaler())
])
categorical_columns = X_train_df.select_dtypes(include=['object','category']).columns
categorical_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='constant', fill_value='NA')),
    ('onehot', preprocessing.OneHotEncoder(sparse=False, handle_unknown='ignore'))
])

print("Number of numerical columns:", len(numeric_columns))
print("Number of categorical columns:", len(categorical_columns))
print("Total number of columns in the dataframe:", X_train_df.shape[1])

Number of numerical columns: 784
Number of categorical columns: 0
Total number of columns in the dataframe: 784

preprocessor = ColumnTransformer(transformers=[
    ('num', numeric_transformer, numeric_columns),
#     ('cat', categorical_transformer, categorical_columns)
])
X_train = preprocessor.fit_transform(X_train_df)
print("Transformed X_train.shape:", X_train.shape)

Transformed X_train.shape: (27455, 784)

# Apply feature scaling and transformation to the test dataset
X_test = preprocessor.transform(X_test_df)
print("Transformed X_test.shape:", X_test.shape)

Transformed X_test.shape: (7172, 784)

3.b) Training Data Balancing

# Not applicable for this iteration of the project

3.c) Display the Final Datasets for Model-Building

# Finalize the training dataset for the modeling activities
class_encoder = preprocessing.LabelEncoder()
y_train = tf.keras.utils.to_categorical(class_encoder.fit_transform(y_train_df))
print("X_train.shape: {} y_train.shape: {}".format(X_train.shape, y_train.shape))

X_train.shape: (27455, 784) y_train.shape: (27455, 24)

# Finalize the test dataset for the modeling activities
y_test = tf.keras.utils.to_categorical(class_encoder.transform(y_test_df))
print("X_test.shape: {} y_test.shape: {}".format(X_test.shape, y_test.shape))

X_test.shape: (7172, 784) y_test.shape: (7172, 24)

if notifyStatus: status_notify('(TensorFlow Multi-Class) Task 3 - Pre-process Data completed on ' + datetime.now().strftime('%A %B %d, %Y %I:%M:%S %p'))

Task 4 - Train and Evaluate Models

if notifyStatus: status_notify('(TensorFlow Multi-Class) Task 4 - Train and Evaluate Models has begun on ' + datetime.now().strftime('%A %B %d, %Y %I:%M:%S %p'))

# Define the function for plotting training results for comparison
def plot_metrics(history):
    fig, axs = plt.subplots(1, 2, figsize=(24, 15))
    metrics =  [train_loss, train_metric]
    for n, metric in enumerate(metrics):
        name = metric.replace("_"," ").capitalize()
        plt.subplot(2,2,n+1)
        plt.plot(history.epoch, history.history[metric], color='blue', label='Train')
        plt.plot(history.epoch, history.history['val_'+metric], color='red', linestyle="--", label='Val')
        plt.xlabel('Epoch')
        plt.ylabel(name)
        # if metric == train_loss:
        #     plt.ylim([0, plt.ylim()[1]])
        # else:
        #     plt.ylim([0.5, 1.1])
        plt.legend()

# Define the default numbers of input/output for modeling
num_inputs = X_train.shape[1]
# number of target classes for multi-class modeling
num_outputs = 24

# Define the baseline model for benchmarking
def create_nn_model(n_inputs=num_inputs, n_outputs=num_outputs, layer1_nodes=256, layer2_nodes=128, layer3_nodes=128, layer4_nodes=64, layer5_nodes=64, 
                    layer1_dropout=0.25, layer2_dropout=0.25, layer3_dropout=0.25, layer4_dropout=0.25, layer5_dropout=0.5, 
                    opt_param=default_optimizer, init_param=default_kernel_init):
    nn_model = keras.Sequential([
        keras.layers.Dense(layer1_nodes, input_shape=(n_inputs,), activation='relu', kernel_initializer=init_param),
        keras.layers.Dropout(layer1_dropout),
        keras.layers.BatchNormalization(),
        keras.layers.Dense(layer2_nodes, activation='relu', kernel_initializer=init_param),
        keras.layers.Dropout(layer2_dropout),
        keras.layers.BatchNormalization(),
        keras.layers.Dense(layer3_nodes, activation='relu', kernel_initializer=init_param),
        keras.layers.Dropout(layer3_dropout),
        keras.layers.BatchNormalization(),
        keras.layers.Dense(layer4_nodes, activation='relu', kernel_initializer=init_param),
        keras.layers.Dropout(layer4_dropout),
        keras.layers.BatchNormalization(),
        keras.layers.Dense(layer5_nodes, activation='relu', kernel_initializer=init_param),
        keras.layers.Dropout(layer5_dropout),
        keras.layers.BatchNormalization(),
        keras.layers.Dense(n_outputs, activation='softmax', kernel_initializer=init_param)
    ])
    nn_model.compile(loss=default_loss, optimizer=opt_param, metrics=default_metrics)
    return nn_model

# Initialize the default model and get a baseline result
startTimeModule = datetime.now()
results = list()
iteration = 0
reset_random(seedNum)
final_model = create_nn_model()
nn_model_history = final_model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=default_epoch, batch_size=default_batch, verbose=1)
print('Total time for model fitting and cross validating:', (datetime.now() - startTimeModule))

Epoch 1/50
858/858 [==============================] - 6s 7ms/step - loss: 3.5323 - accuracy: 0.0644 - val_loss: 2.7429 - val_accuracy: 0.2295
Epoch 2/50
858/858 [==============================] - 6s 7ms/step - loss: 3.0846 - accuracy: 0.1254 - val_loss: 2.3555 - val_accuracy: 0.3182
Epoch 3/50
858/858 [==============================] - 6s 7ms/step - loss: 2.7340 - accuracy: 0.1879 - val_loss: 2.0565 - val_accuracy: 0.4221
Epoch 4/50
858/858 [==============================] - 6s 7ms/step - loss: 2.4141 - accuracy: 0.2590 - val_loss: 1.8139 - val_accuracy: 0.4870
Epoch 5/50
858/858 [==============================] - 6s 7ms/step - loss: 2.1650 - accuracy: 0.3194 - val_loss: 1.6265 - val_accuracy: 0.5130
Epoch 6/50
858/858 [==============================] - 6s 6ms/step - loss: 1.9424 - accuracy: 0.3793 - val_loss: 1.4506 - val_accuracy: 0.5715
Epoch 7/50
858/858 [==============================] - 6s 6ms/step - loss: 1.7503 - accuracy: 0.4367 - val_loss: 1.2920 - val_accuracy: 0.6196
Epoch 8/50
858/858 [==============================] - 6s 7ms/step - loss: 1.5761 - accuracy: 0.4901 - val_loss: 1.1655 - val_accuracy: 0.6602
Epoch 9/50
858/858 [==============================] - 6s 7ms/step - loss: 1.4147 - accuracy: 0.5395 - val_loss: 1.0554 - val_accuracy: 0.6613
Epoch 10/50
858/858 [==============================] - 6s 7ms/step - loss: 1.2827 - accuracy: 0.5871 - val_loss: 1.0098 - val_accuracy: 0.6619
Epoch 11/50
858/858 [==============================] - 5s 6ms/step - loss: 1.1537 - accuracy: 0.6243 - val_loss: 0.9243 - val_accuracy: 0.6861
Epoch 12/50
858/858 [==============================] - 6s 6ms/step - loss: 1.0524 - accuracy: 0.6550 - val_loss: 0.9070 - val_accuracy: 0.6857
Epoch 13/50
858/858 [==============================] - 6s 7ms/step - loss: 0.9760 - accuracy: 0.6800 - val_loss: 0.8879 - val_accuracy: 0.6857
Epoch 14/50
858/858 [==============================] - 6s 7ms/step - loss: 0.8878 - accuracy: 0.7087 - val_loss: 0.8669 - val_accuracy: 0.7047
Epoch 15/50
858/858 [==============================] - 5s 6ms/step - loss: 0.8214 - accuracy: 0.7273 - val_loss: 0.8030 - val_accuracy: 0.7093
Epoch 16/50
858/858 [==============================] - 6s 6ms/step - loss: 0.7424 - accuracy: 0.7551 - val_loss: 0.8406 - val_accuracy: 0.7128
Epoch 17/50
858/858 [==============================] - 6s 6ms/step - loss: 0.7047 - accuracy: 0.7654 - val_loss: 0.8442 - val_accuracy: 0.7132
Epoch 18/50
858/858 [==============================] - 5s 6ms/step - loss: 0.6403 - accuracy: 0.7839 - val_loss: 0.8343 - val_accuracy: 0.7234
Epoch 19/50
858/858 [==============================] - 6s 7ms/step - loss: 0.5971 - accuracy: 0.8021 - val_loss: 0.8392 - val_accuracy: 0.7250
Epoch 20/50
858/858 [==============================] - 6s 7ms/step - loss: 0.5700 - accuracy: 0.8080 - val_loss: 0.8813 - val_accuracy: 0.7193
Epoch 21/50
858/858 [==============================] - 5s 6ms/step - loss: 0.5332 - accuracy: 0.8220 - val_loss: 0.8691 - val_accuracy: 0.7220
Epoch 22/50
858/858 [==============================] - 6s 7ms/step - loss: 0.5108 - accuracy: 0.8263 - val_loss: 0.9057 - val_accuracy: 0.7217
Epoch 23/50
858/858 [==============================] - 6s 7ms/step - loss: 0.4773 - accuracy: 0.8406 - val_loss: 0.8623 - val_accuracy: 0.7333
Epoch 24/50
858/858 [==============================] - 6s 7ms/step - loss: 0.4604 - accuracy: 0.8468 - val_loss: 0.9004 - val_accuracy: 0.7278
Epoch 25/50
858/858 [==============================] - 6s 7ms/step - loss: 0.4269 - accuracy: 0.8575 - val_loss: 0.8835 - val_accuracy: 0.7368
Epoch 26/50
858/858 [==============================] - 5s 6ms/step - loss: 0.4119 - accuracy: 0.8633 - val_loss: 0.9203 - val_accuracy: 0.7308
Epoch 27/50
858/858 [==============================] - 6s 7ms/step - loss: 0.4073 - accuracy: 0.8652 - val_loss: 0.9358 - val_accuracy: 0.7253
Epoch 28/50
858/858 [==============================] - 6s 7ms/step - loss: 0.3779 - accuracy: 0.8772 - val_loss: 0.9707 - val_accuracy: 0.7377
Epoch 29/50
858/858 [==============================] - 6s 7ms/step - loss: 0.3720 - accuracy: 0.8797 - val_loss: 0.9794 - val_accuracy: 0.7351
Epoch 30/50
858/858 [==============================] - 6s 7ms/step - loss: 0.3439 - accuracy: 0.8896 - val_loss: 0.9411 - val_accuracy: 0.7521
Epoch 31/50
858/858 [==============================] - 6s 7ms/step - loss: 0.3365 - accuracy: 0.8930 - val_loss: 0.9908 - val_accuracy: 0.7529
Epoch 32/50
858/858 [==============================] - 6s 7ms/step - loss: 0.3379 - accuracy: 0.8929 - val_loss: 1.0078 - val_accuracy: 0.7455
Epoch 33/50
858/858 [==============================] - 6s 7ms/step - loss: 0.3025 - accuracy: 0.9072 - val_loss: 1.0196 - val_accuracy: 0.7457
Epoch 34/50
858/858 [==============================] - 6s 7ms/step - loss: 0.2939 - accuracy: 0.9120 - val_loss: 1.0528 - val_accuracy: 0.7494
Epoch 35/50
858/858 [==============================] - 5s 6ms/step - loss: 0.2936 - accuracy: 0.9103 - val_loss: 1.0357 - val_accuracy: 0.7535
Epoch 36/50
858/858 [==============================] - 5s 6ms/step - loss: 0.2792 - accuracy: 0.9175 - val_loss: 1.0467 - val_accuracy: 0.7538
Epoch 37/50
858/858 [==============================] - 6s 7ms/step - loss: 0.2700 - accuracy: 0.9205 - val_loss: 1.0724 - val_accuracy: 0.7522
Epoch 38/50
858/858 [==============================] - 6s 7ms/step - loss: 0.2605 - accuracy: 0.9244 - val_loss: 1.0465 - val_accuracy: 0.7602
Epoch 39/50
858/858 [==============================] - 6s 7ms/step - loss: 0.2558 - accuracy: 0.9242 - val_loss: 1.0413 - val_accuracy: 0.7627
Epoch 40/50
858/858 [==============================] - 6s 7ms/step - loss: 0.2341 - accuracy: 0.9319 - val_loss: 1.0052 - val_accuracy: 0.7810
Epoch 41/50
858/858 [==============================] - 6s 6ms/step - loss: 0.2382 - accuracy: 0.9332 - val_loss: 1.0054 - val_accuracy: 0.7736
Epoch 42/50
858/858 [==============================] - 6s 7ms/step - loss: 0.2211 - accuracy: 0.9377 - val_loss: 1.0945 - val_accuracy: 0.7586
Epoch 43/50
858/858 [==============================] - 5s 6ms/step - loss: 0.2146 - accuracy: 0.9401 - val_loss: 1.0469 - val_accuracy: 0.7692
Epoch 44/50
858/858 [==============================] - 6s 7ms/step - loss: 0.2126 - accuracy: 0.9405 - val_loss: 1.0682 - val_accuracy: 0.7790
Epoch 45/50
858/858 [==============================] - 6s 7ms/step - loss: 0.2123 - accuracy: 0.9420 - val_loss: 1.0883 - val_accuracy: 0.7708
Epoch 46/50
858/858 [==============================] - 6s 7ms/step - loss: 0.1976 - accuracy: 0.9459 - val_loss: 1.1273 - val_accuracy: 0.7581
Epoch 47/50
858/858 [==============================] - 6s 7ms/step - loss: 0.2082 - accuracy: 0.9427 - val_loss: 1.1329 - val_accuracy: 0.7595
Epoch 48/50
858/858 [==============================] - 6s 6ms/step - loss: 0.1973 - accuracy: 0.9460 - val_loss: 1.0786 - val_accuracy: 0.7716
Epoch 49/50
858/858 [==============================] - 6s 7ms/step - loss: 0.1924 - accuracy: 0.9488 - val_loss: 1.1085 - val_accuracy: 0.7653
Epoch 50/50
858/858 [==============================] - 6s 7ms/step - loss: 0.1863 - accuracy: 0.9493 - val_loss: 1.0900 - val_accuracy: 0.7793
Total time for model fitting and cross validating: 0:04:54.323254

plot_metrics(nn_model_history)

# Summarize the final model
final_model.summary()

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense (Dense)                (None, 256)               200960    
_________________________________________________________________
dropout (Dropout)            (None, 256)               0         
_________________________________________________________________
batch_normalization (BatchNo (None, 256)               1024      
_________________________________________________________________
dense_1 (Dense)              (None, 128)               32896     
_________________________________________________________________
dropout_1 (Dropout)          (None, 128)               0         
_________________________________________________________________
batch_normalization_1 (Batch (None, 128)               512       
_________________________________________________________________
dense_2 (Dense)              (None, 128)               16512     
_________________________________________________________________
dropout_2 (Dropout)          (None, 128)               0         
_________________________________________________________________
batch_normalization_2 (Batch (None, 128)               512       
_________________________________________________________________
dense_3 (Dense)              (None, 64)                8256      
_________________________________________________________________
dropout_3 (Dropout)          (None, 64)                0         
_________________________________________________________________
batch_normalization_3 (Batch (None, 64)                256       
_________________________________________________________________
dense_4 (Dense)              (None, 64)                4160      
_________________________________________________________________
dropout_4 (Dropout)          (None, 64)                0         
_________________________________________________________________
batch_normalization_4 (Batch (None, 64)                256       
_________________________________________________________________
dense_5 (Dense)              (None, 24)                1560      
=================================================================
Total params: 266,904
Trainable params: 265,624
Non-trainable params: 1,280
_________________________________________________________________

if notifyStatus: status_notify('(TensorFlow Multi-Class) Task 4 - Train and Evaluate Models completed on ' + datetime.now().strftime('%A %B %d, %Y %I:%M:%S %p'))

Task 5 - Finalize Model and Present Analysis

if notifyStatus: status_notify('(TensorFlow Multi-Class) Task 5 - Finalize Model and Present Analysis has begun on ' + datetime.now().strftime('%A %B %d, %Y %I:%M:%S %p'))

# Not applicable for this iteration of modeling

if notifyStatus: status_notify('(TensorFlow Multi-Class) Task 5 - Finalize Model and Present Analysis completed on ' + datetime.now().strftime('%A %B %d, %Y %I:%M:%S %p'))

print ('Total time for the script:',(datetime.now() - startTimeScript))

Total time for the script: 0:08:21.144189